Fully automated video based pedestrian detection and tracking is a challenging task with many practical and important applications. We present our work aimed to allow robust and simultaneously close to real-time tracking of pedestrians. The presented approach is stable to occlusions, lighting conditions and is generalized to be applied on arbitrary video data. The core tracking approach is built upon tracking-by-detections principle. We describe our cascaded HOG detector with successive CNN verification in detail. For the tracking and re-identification task, we did an extensive analysis of appearance based features as well as their combinations. The tracker was tested on many hours of video data for different scenarios; the results are presented and discussed.
We present a system for trash can detection and counting from a camera which is mounted on a garbage collection truck. A working prototype has been successfully implemented and tested with several hours of real-world video. The detection pipeline consists of HOG detectors for two trash can sizes, and meanshift tracking and low level image processing for the analysis of the garbage disposal process. Considering the harsh environment and unfavorable imaging conditions, the process works already good enough so that very useful measurements from video data can be extracted. The false positive/false negative rate of the full processing pipeline is about 5-6% at fully automatic operation. Video data of a full day (about 8 hrs) can be processed in about 30 minutes on a standard PC.
Reliable automatic detection of traffic jam occurrences is of big significance for traffic flow analysis related applications. We present our work aimed at the application of video based real-time traffic jam detection. Our method can handle both calibrated and un-calibrated scenarios, operating in world and in image coordinate systems respectively. The method is designed to be operated on a smart camera, but is also suitable for a standard personal computer. The combination of state-of-the-art algorithms for vehicle detections and velocity estimation allows robust long-term system operation in due to the high recall rate and very low false alarm rate. The proposed method not only detects traffic jam events in real-time, but also precisely localizes traffic jams by their start and end positions per road lane. We describe also our strategy in making computationally heavy algorithms real-time capable even on hardware with a limited computing power.
This paper presents our work towards robust vehicle detection in dynamic and static scenes from a brief historical perspective up to our current state-of-the-art. We cover several methods (PCA, basic HOG, texture analysis, 3D measurement) which have been developed for, tested, and used in real-world scenarios. The second part of this work presents a new HOG cascade training algorithm which is based on evolutionary optimization principles: HOG features for a low stage count cascade are learned using genetic feature selection methods. We show that with this approach it is possible to create a HOG cascade which has comparable performance to an AdaBoost trained cascade, but is much faster to evaluate.
The efficient and robust detection of the presence of vehicles in restricted parking areas is important for applications in law enforcement as well as for the enforcement of parking rules on private property. We present our work towards this goal aimed at the application of vehicle detection in urban environments. The method is to be suited for smart cameras which have to operate autonomously over extended periods of time. Our system is developed as part of a bigger research effort which combines onsite vehicle presence detection and an associated web management system which is intended to monitor, steer and reroute delivery vehicles.
This paper addresses the identity switching problem of a tracking by detection approach. When matching a newly found detection to a known trajectory in certain circumstances (e.g. occlusions) the trajectory will switch from one object to another decreasing the overall quality. To overcome this problem four keypoint based approaches are investigated. The keypoint based approaches rely on finding interesting points on and around the tracked object and describing them in a discriminant way. In the verification step the known trajectory keypoint descriptions are matched to the newly calculated detection keypoint description and according to a distance measure, the match is accepted or rejected. Another two approaches which provide abstract representations of the objects are also reviewed. Finally the verification approaches are tested on a publicly available pedestrian data set which shows a crowded town centre.
The observation and monitoring of traffic with smart vision systems for the purpose of improving traffic safety has a big potential. Embedded vision systems can count vehicles and estimate the state of traffic along the road, they can supplement or replace loop sensors with their limited local scope, radar which measures the speed, presence and number of vehicles. This work presents a vision system which has been built to detect and report traffic rule violations at unsecured railway crossings which pose a threat to drivers day and night. Our system is designed to detect and record vehicles passing over the railway crossing after the red light has been activated. Sparse optical flow in conjunction with motion clustering is used for real-time motion detection in order to capture these safety critical events. The cameras are activated by an electrical signal from the railway when the red light turns on. If they detect a vehicle moving over the stopping line, and it is well over this limit, an image sequence will be recorded and stored onboard for later evaluation. The system has been designed to be operational in all weather conditions, delivering human-readable license plate images even under the worst illumination conditions like direct incident sunlight direct view into or vehicle headlights. After several months of operation in the field we can report on the performance of the system, its hardware implementation as well as the implementation of algorithms which have proven to be usable in this real-world application.
The observation and monitoring of traffic with smart visions systems for the purpose of improving traffic safety has a big potential. Today the automated analysis of traffic situations is still in its infancy--the patterns of vehicle motion and pedestrian flow in an urban environment are too complex to be fully captured and interpreted by a vision system. 3In this work we present steps towards a visual monitoring system which is designed to detect potentially dangerous traffic situations around a pedestrian crossing at a street intersection. The camera system is specifically designed to detect incidents in which the interaction of pedestrians and vehicles might develop into safety critical encounters. The proposed system has been field-tested at a real pedestrian crossing in the City of Vienna for the duration of one year. It consists of a cluster of 3 smart cameras, each of which is built from a very compact PC hardware system in a weatherproof housing. Two cameras run vehicle detection and tracking software, one camera runs a pedestrian detection and tracking module based on the HOG dectection principle. All 3 cameras use sparse optical flow computation in a low-resolution video stream in order to estimate the motion path and speed of objects. Geometric calibration of the cameras allows us to estimate the real-world co-ordinates of detected objects and to link the cameras together into one common reference system. This work describes the foundation for all the different object detection modalities (pedestrians, vehicles), and explains the system setup, tis design, and evaluation results which we have achieved so far.
The observation and monitoring of traffic witih smart vision systems for the purpose of improving traffic safety has a big potential. Embedded loop sensors can detect and count passing vehicles, radar can measure speed and presence of vehicles, and embedded vision systems or stationary camera systems can count vehicles and estimate the state of traffic along the road. This work presents a vision system which is targeted at detecting and reporting incidents at unsecured railways crossings. These crossings, even when guarded by automated barriers, pose a threat to drivers day and night. Our system is designed to detect and record vehicles which pass over the railway crossing by means of real-time motion analysis after the red light has been activated. We implement sparse optical flow in conjunction with motion clustering in order to detect critical events. We describe some modifications of the original Lucas Kanade optical flow method which makes our implementation faster and more robust compared to the original concept. In addition, the results of our optical flow method are compared with a HOG based vehicle detector which has been implemented and tested as an alternative methodology. The embedded system which is used for detection consists of a smart camera which observes one street lane as* well as the red light at the crossing. The camera is triggered by an electrical signal from the railway as soon ss a vehicle moves over th this line, image sequences are recorded and stored onboard the device.
The transportation of hazardous goods in public streets systems can pose severe safety threats in case of accidents.
One of the solutions for these problems is an automatic detection and registration of vehicles which are marked
with dangerous goods signs. We present a prototype system which can detect a trained set of signs in high
resolution images under real-world conditions. This paper compares two different methods for the detection:
bag of visual words (BoW) procedure and our approach presented as pairs of visual words with Hough voting.
The results of an extended series of experiments are provided in this paper. The experiments show that the
size of visual vocabulary is crucial and can significantly affect the recognition success rate. Different code-book
sizes have been evaluated for this detection task. The best result of the first method BoW was 67% successfully
recognized hazardous signs, whereas the second method proposed in this paper - pairs of visual words and Hough
voting - reached 94% of correctly detected signs. The experiments are designed to verify the usability of the two
proposed approaches in a real-world scenario.
The detection of pose invariant planar patterns has many practical applications in computer vision and surveillance
systems. The recognition of company logos is used in market studies to examine the visibility and frequency of logos in
advertisement. Danger signs on vehicles could be detected to trigger warning systems in tunnels, or brand detection on
transport vehicles can be used to count company-specific traffic. We present the results of a study on planar pattern
detection which is based on keypoint detection and matching of distortion invariant 2d feature descriptors. Specifically
we look at the keypoint detectors of type: i) Lowe's DoG approximation from the SURF algorithm, ii) the Harris Corner
Detector, iii) the FAST Corner Detector and iv) Lepetit's keypoint detector. Our study then compares the feature
descriptors SURF and compact signatures based on Random Ferns: we use 3 sets of sample images to detect and match
3 logos of different structure to find out which combinations of keypoint detector/feature descriptors work well.
A real-world test tries to detect vehicles with a distinctive logo in an outdoor environment under realistic lighting and
weather conditions: a camera was mounted on a suitable location for observing the entrance to a parking area so that
incoming vehicles could be monitored. In this 2 hour long recording we can successfully detect a specific company logo
without false positives.
The observation and monitoring of traffic with smart visions systems for the purpose of improving traffic safety has a
big potential. For example embedded vision systems built into vehicles can be used as early warning systems, or
stationary camera systems can modify the switching frequency of signals at intersections. Today the automated analysis
of traffic situations is still in its infancy - the patterns of vehicle motion and pedestrian flow in an urban environment are
too complex to be fully understood by a vision system.
We present steps towards such a traffic monitoring system which is designed to detect potentially dangerous traffic
situations, especially incidents in which the interaction of pedestrians and vehicles might develop into safety critical
encounters. The proposed system is field-tested at a real pedestrian crossing in the City of Vienna for the duration of one
year. It consists of a cluster of 3 smart cameras, each of which is built from a very compact PC hardware system in an
outdoor capable housing.
Two cameras run vehicle detection software including license plate detection and recognition, one camera runs a
complex pedestrian detection and tracking module based on the HOG detection principle. As a supplement, all 3
cameras use additional optical flow computation in a low-resolution video stream in order to estimate the motion path
and speed of objects. This work describes the foundation for all 3 different object detection modalities (pedestrians,
vehi1cles, license plates), and explains the system setup and its design.
KEYWORDS: Cameras, Imaging systems, Global Positioning System, Calibration, 3D metrology, 3D modeling, Data acquisition, Sensors, Detection and tracking algorithms, Video
Ski jumping has continuously raised major public interest since the early 70s of the last century, mainly in Europe and
Japan. The sport undergoes high-level analysis and development, among others, based on biodynamic measurements
during the take-off and flight phase of the jumper. We report on a vision-based solution for such measurements that
provides a full 3D trajectory of unique points on the jumper's shape. During the jump synchronized stereo images are
taken by a calibrated camera system in video rate. Using methods stemming from video surveillance, the jumper is
detected and localized in the individual stereo images, and learning-based deformable shape analysis identifies the
jumper's silhouette. The 3D reconstruction of the trajectory takes place on standard stereo forward intersection of
distinct shape points, such as helmet top or heel. In the reported study, the measurements are being verified by an
independent GPS measurement mounted on top of the Jumper's helmet, synchronized to the timing of camera exposures.
Preliminary estimations report an accuracy of +/-20 cm in 30 Hz imaging frequency within 40m trajectory. The system is
ready for fully-automatic on-line application on ski-jumping sites that allow stereo camera views with an approximate
base-distance ratio of 1:3 within the entire area of investigation.
Object detection and tracking play an increasing role in modern surveillance systems. Vision
research is still confronted with many challenges when it comes to robust tracking in realistic
imaging scenarios. We describe a tracking framework which is aimed at the detection and tracking
of objects in real-world situations (e.g. from surveillance cameras) and in real-time. Although the
current system is used for pedestrian tracking only, it can easily be adapted to other detector types
and object classes. The proposed tracker combines i) a simple background model to speed up all
following computations, ii)1 a fast object detector realized with a cascaded HOG detector, iii)
motion estimation with a KLT Tracker iv) object verification based on texture/color analysis by
means of DCT coefficients and , v) dynamic trajectory and object management. The tracker has
been successfully applied in indoor and outdoor scenarios it a public transportation hub in the City
of Graz, Austria.
KEYWORDS: Data modeling, Image processing, Detection and tracking algorithms, Sensors, Surveillance, Cameras, Shape analysis, 3D modeling, Process modeling, Video
The detection of pedestrians in real-world scenes is a daunting task, especially in crowded situations. Our experience
over the last years has shown that active shape models (ASM) can contribute significantly to a robust pedestrian
detection system.
The paper starts with an overview of shape model approaches, it then explains our approach which builds on top of
Eigenshape models which have been trained using real-world data. These models are placed over candidate regions and
matched to image gradients using a scoring function which integrates i) point distribution, ii) local gradient orientations
iii) local image gradient strengths. A matching and shape model update process is iteratively applied in order to fit the
flexible models to the local image content.
The weights of the scoring function have a significant impact on the ASM performance. We analyze different settings of
scoring weights for gradient magnitude, relative orientation differences, distance between model and gradient in an
experiment which uses real-world data. Although for only one pedestrian model in an image computation time is low, the
number of necessary processing cycles which is needed to track many people in crowded scenes can become the
bottleneck in a real-time application. We describe the measures which have been taken in order to improve the speed of
the ASM implementation and make it real-time capable.
This paper describes the implementation of a pedestrian detection system which is based on the Histogram of Oriented
Gradients (HOG) principle and which tries to improve the overall detection performance by combining several part
based detectors in a simple voting scheme. The HOG feature based part detectors are specifically trained for head, head-left,
head-right, and left/right sides of people, assuming that these parts should be recognized even in very crowded
environments like busy public transportation platforms. The part detectors are trained on the INRIA people image
database using a polynomial Support Vector Machine. Experiments are undertaken with completely different test
samples which have been extracted from two imaging campaigns in an outdoor setup and in an underground station. Our
results demonstrate that the performance of pedestrian detection degrades drastically in very crowded scenes, but that
through the combination of part detectors a gain in robustness and detection rate can be achieved at least for classifier
settings which yield very low false positive rates.
KEYWORDS: Image segmentation, Inspection, 3D modeling, RGB color model, 3D metrology, Hough transforms, Convolution, 3D image processing, Cameras, Image processing
One of the most important monitoring tasks of tunnel inspection is the observation of cracks. This paper describes an approach for crack following using mid-resolution (2-5mm per pixel) images of the tunnel surface. A mosaic on the basis of the tunnel design surface is built from images taken with a mobile platform. On this image representing the unwrapped tunnel surface texture the starting points of each crack are found semiautomatically using a modified Hough transform. Crack following takes place on the basis of local line fitting and exhaustive search in both directions of the crack, taking into account several restrictions, rules and optimization criteria to find the correct crack trajectory. A practical implementation polygonizes the extracted cracks and feeds them into a tunnel inspection data base. The method is applicable to various types of background texture as expected in the tunnel environment.
This paper describes a close to real-time scale invariant implementation of a pedestrian detector system which is based on the Histogram of Oriented Gradients (HOG) principle. Salient HOG features are first selected from a manually created very large database of samples with an evolutionary optimization procedure that directly trains a polynomial Support Vector Machine (SVM). Real-time operation is achieved by a cascaded 2-step classifier which uses first a very fast linear SVM (with the same features as the polynomial SVM) to reject most of the irrelevant detections and then computes the decision function with a polynomial SVM on the remaining set of candidate detections. Scale invariance is achieved by running the detector of constant size on scaled versions of the original input images and by clustering the results over all resolutions. The pedestrian detection system has been implemented in two versions: i) fully body detection, and ii) upper body only detection. The latter is especially suited for very busy and crowded scenarios. On a state-of-the-art PC it is able to run at a frequency of 8 - 20 frames/sec.
State of the art algorithms for people or vehicle detection should not only be accurate in terms of detection performance and low false alarm rate, but also fast enough for real time applications. Accurate algorithms are usually very complex and tend to have a lot of calculated features to be used or parameters available for adjustments. So one big goal is to decrease the amount of necessary features used for object detection while increasing the speed of the algorithm and overall performance by finding an optimum set of classifier variables. In this paper we describe algorithms for feature selection, parameter optimisation and pattern matching especially for the task of pedestrian detection based on Histograms of Oriented Gradients and Support Vector Machine classifiers. Shape features were derived with the Histogram of Oriented Gradients algorithm which resulted in a feature vector of 6318 elements. To decrease computation time to an acceptable limit for real-time detection we reduced the full feature vector to sizes of 1000, 500, 300, 200, and 160 elements with a genetic feature selection method. With the remaining features a Support Vector Machine classifier was build and its classification parameters further optimized to result in less support vectors for further improvements in processing speed. This paper compares the classification performance, of the different SVM's on real videos (some sample images), visualizes the chosen features (which histogram bins on which location in the image search feature) and analyses the performance of the final system with respect to execution time and frame rate.
The efficient monitoring of traffic flow as well as related surveillance and detection applications demand an increasingly robust recognition of vehicles in image and video data. This paper describes two different methods for vehicle detection in real world situations: Principal Component Analysis and the Histogram of Gradients principle. Both methods are described and their detection capabilities as well as advantages and disadvantages are compared. A large sample dataset which contains images of cars from the backside and frontside in day and night conditions is the basis for creating and optimizing both variants of the proposed algorithms. The resulting two detectors allow recognition of vehicles in frontal view +- 30 deg and views from behind +- 30 deg. The paper demonstrates that both detection methods can operate effectively even under difficult lighting situations with high detection rates and a low number of false positives.
Continuous monitoring and control of process temperature(s) is one of the cornerstones in high quality steel making. Given the very high temperatures in the liquid phase of the steel and the slag on top of the steel (approx. 1500oC...1800oC) and the particularly harsh environment at the manufacturing plant, only very few temperature sensors are able to cope with the process requirements, in particular a wide variety of thermocouple probes and pyrometers are commonly used. More recently thermography infrared cameras have begun to enter the scenario but are often discarded as an option mainly because of their high cost. In the high temperature range as described above a dual wavelength camera solution working in the visible part of the spectrum offers a viable alternative1. At a fraction of the cost such a system can deliver images of high spatial resolution while at the same time measuring temperature with an accuracy of better than 5oC. The thermal camera approach is particularly beneficial in the present case where important process information can be deducted from quantitative observation of the flow patterns of the molten material which could until now only be estimated by a trained operator with all the drawbacks inherent to such an approach. The thermal camera solution thus offers a clear technological advantage for the steel manufacturer.
A vision system designed to detect people in complex backgrounds is presented. The purpose of the proposed algorithms is to allow the identification and tracking of single persons under difficult conditions - in crowded places, under partial occlusion and in low resolution images. In order to detect people reliably, we combine different information channels from video streams. Most emphasis for the initialization of trajectories and the subsequent pedestrian recognition is placed on the detection of the head-shoulder contour. In the first step a simple and fast shape model selects promising candidates, then a local active shape model is matched against the gradients found in the image with the help of a cost function.
Texture analysis in the form of co-occurrence features ensures that shape candidates form coherent trajectories over time. In order to reduce the amount of false positives and to become more robust, a pattern analysis step based on Eigenimage analysis is presented.
The cues which form the basis of pedestrian detection are integrated into a tracking algorithm which uses the shape information for initial pedestrian detection and verification, propagates positions into new frames using local motion and matches pedestrians with the help of texture information.
A shape matching framework designed for an industrial application is presented. The task of the proposed system is to identify and sort plastic teeth, used by dentists, based on their 2D shape only. A sorting machine puts each tooth on a predefined location under a camera which is equipped with a telecentric lens. From the resulting image the contour of the object is extracted and compared with a database of reference teeth. In order to cope with the problem that a tooth may rest on several (typically 4 - 15) stable positions when placed under the camera, all its proper contours are stored as valid tooth representations. In total the tooth database used for tests contained 171 teeth represented by 1257 contours of 1000 points each. Under the constraint that one contour out of 1257 has to be identified in less than one second, we describe the algorithmic approach which has successfully led to the implementation of the system. A fast pre-selection of shapes and the repeated calculation of point transforms to match them with the reference contours makes up the underlying principle of the proposed system. In addition to the decisions actually made during the design of the system we describe several possible enhancements which can further improve the speed and generality of our matching approach.
A machine vision application for the fully automatic straightening of steel bars is presented. The bars with lengths of up to 6000 mm are quite bent on exit of the rolling mill and need to be straightened prior to delivery to a customer. The shape of the steel bar is extracted and measured by two video resolution cameras which are calibrated in position and viewing angle relative to a coordinate system located in the center of the roller table. Its contour is tracked and located with a dynamic programming method utilizing several constraints to make the algorithm as robust as possible. 3D camera calibration allows the transformation of image coordinates to real-world coordinates. After smoothing and spline fitting the curvature of the bar is computed. A deformation model of the effect of force applied to the steel allows the system to generate press commands which state where and with what specific pressure the bar has to be processed. The model can be used to predict the straightening of the bar over some consecutive pressing events helping to optimize the operation. The process of measurement and pressing is repeated until the straightness of the bar reaches a predefined limit.
An accurate method to detect and classify military vehicles based on the recognition of shapes is presented in this work. FFT-Descriptors are used to generate a scale, translation and rotation invariant characterization of the shape of such an object. By interpreting the boundary pixels of an object as complex numbers it is possible to calculate an FFT-Descriptor based on the spectrum of a Fast Fourier Transform of these numbers. It is shown that by using this characterization it is possible to match such representations with models in a database of known vehicles and thereby gaining a highly robust and fault tolerant object classification. By selecting a specific number of components of a FFT-Descriptor the classification process can by tailored to different needs of recognition accuracy, allowed shape deviation and classification speed.
Within the European Mars Express Mission to be launched 2003 the Beagle2 Lander will foresee the access to stereoscopic views of the surrounding Martian surface after touchdown. For scientific purposes the necessity for a high resolution three dimensional (3D) reconstruction of the landing site is evident. A lander vision subsystem capable of reconstructing the landing site and its vicinity using a stereo camera mounted on the robotic arm of the lander is used therefore. Knowledge about the geometric camera features (position and pointing with respect to each other, position and pointing with respect to the lander, intrinsic parameters and lens distortion) are determined in a calibration step on ground before takeoff. The 3D reconstruction of the landing site is performed after landing by means of stereo matching using the transmitted images. Merging several stereo reconstructions uses the respective robotic arm states during image acquisition for calibration. This paper describes the full processing chain consisting of calibration of the sensor system, stereo matching, 3D reconstruction and merging of results. Emphasis is laid on the stereo reconstruction step. A software system configuration is proposed. Tests using Mars Pathfinder images as example data show the feasibility of the approach and give accuracy estimations.
A fast and efficient method for the detection and recognition of objects which have similar, but not identical, contours is presented. Arbitrary shapes are characterized by interpreting their boundary points as complex numbers and generating spectra from those representations using the Fast Fourier Transform. Suitable normalization of those spectral components leads to a translation, scale and rotation invariant description of each shape. A similarity measure which is based on a simple distance calculation of the spectral magnitude components is used to classify each new shape. By selecting a specific number of spectral components (lower frequencies describe coarse obj ect details, higher frequencies explain fine details) the whole recognition process may be easily tailored to specific needs of recognition accuracy, performance and allowed shape deviation. Besides the compactness of object description, our proposed algorithm for shape recognition can be very efficiently implemented and executed in real-time on standard PC hardware
One approach to stereo matching is to use different local features to find correspondences. The selection of an optimum feature set is the content of this paper. An operational software tool based on the principle of comparing feature vectors is used for stereo matching. A relatively large set of different local features is sought for optimum combinations of 6 - 10 of them. This is done by a genetic process that uses an intrinsic quality criterion that evaluates the correctness of each individual match. The convergence of the genetic feature selection process is demonstrated on a real stereo pair of a tunnel surface. Four areas were used for individual optimization. After several hundred generations for each of the areas, it is shown that the identified feature sets result in a considerably better stereo matching result than the currently used features, which were the result of an initial manual choice. The experiments described in this paper use a `super-set' of 145 features for every pixel, which are created by filtering the image with convolution kernels (averaging, Gaussian filters, bandpass, highpass), median filters and Gabor kernels. From these 145 filters, the genetic feature selection process selects an optimal set of operators. Using the selected filters results in a 15% improvement of the matching accuracy and robustness.
This paper deals with the recovery of a scene from a pair of images, where each image is acquired from a different viewpoint. The central problem is the identification of corresponding points in all views. We use the feature-based approach to find corresponding points.Various types of features have been sued previously, where Gabor features showed significant advantages in terms of accuracy and the complexity/accuracy trade-off. The accuracy is measured as the rate of correctly associated pixels The accuracy measures are found by comparing the disparity maps produced by the matching program with the correct disparities. These correct disparities must be known, and are typically produced by expensive photogrammetric techniques. In this paper we show a method of gauging the performance of a stereo by expensive photogrammetric techniques. In this paper we show a method of gauging the performance of a stereo matcher without the necessity of such a reference disparity date set. We show that statistics on the back-matching distances can be used instead. these are a by- product of the matching process. This opens the door to extensive testing and optimization, since we no longer have to rely on the existence of the reference disparities.
This paper deals with the recovery of a scene from a pair of images, where each image is acquired from a different viewpoint. The central problem is the identification of corresponding points in all views. We use the feature-based approach to find corresponding points. Various types of features have been used previously, where Gabor features showed significant advantages in terms of accuracy and the complexity/accuracy trade-off. The accuracy is measured as the rate of correctly associated pixels. The matching process typically results in a certain number of ambiguous positions, where the best match found is not the desired match. The main contribution of this paper lies in the application of a genetic algorithm for feature selection. This method uses the previously illustrated fact that the amount of ambiguity in the matching process can be quantitatively measured via statistics on the back-matching distances. With this method, the quality of a matching result can be measured without reference disparity data (or ground truth). The fitness function required for the application of genetic feature optimization is defined using these back-matching statistics. The output of the genetic algorithm is an improved feature set, which contains fewer features as the initial set, but yields extremely improved accuracy. We show that the accuracy of the matching result can be much improved by our genetic optimization approach, and we describe the experiments illustrating the results.
An image acquisition and processing algorithm for inspection of tire treads has been developed. The tire treads are flat strips of black rubber material used as the main component in retreading automobile tires. These treads have a complex molded design on one side (DESIGN SIDE) and a flat surface on the other side. The inspection of the Design Side of the tread is one of the key operations in the tread fabrication process impacting quality and consistency of the final product. This paper will discuss development of the main optical inspection algorithms utilized in the system design. The algorithms described in this paper were tested in the laboratory prototype of the inspection system and will be implemented in the final production system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.