The detection and tracking of moving dim target in infrared image have been an research hotspot for many years. The target in each frame of images only occupies several pixels without any shape and structure information. Moreover, infrared small target is often submerged in complicated background with low signal-to-clutter ratio, making the detection very difficult. Different backgrounds exhibit different statistical properties, making it becomes extremely complex to detect the target. If the threshold segmentation is not reasonable, there may be more noise points in the final detection, which is unfavorable for the detection of the trajectory of the target. Single-frame target detection may not be able to obtain the desired target and cause high false alarm rate. We believe the combination of suspicious target detection spatially in each frame and temporal association for target tracking will increase reliability of tracking dim target. The detection of dim target is mainly divided into two parts, In the first part, we adopt bilateral filtering method in background suppression, after the threshold segmentation, the suspicious target in each frame are extracted, then we use LSTM(long short term memory) neural network to predict coordinates of target of the next frame. It is a brand-new method base on the movement characteristic of the target in sequence images which could respond to the changes in the relationship between past and future values of the values. Simulation results demonstrate proposed algorithm can effectively predict the trajectory of the moving small target and work efficiently and robustly with low false alarm.
Symmetry axis extraction is an important part of the image feature detection. So far, various classical symmetry axes extraction algorithms have been proposed, such as the minimum-inertia-axis-based method, the SIFT-based method. If the input image is blurry, or it’s difficult to extract feature points or corner points from input images, however, the above algorithms are difficult to obtain satisfied results. This paper presents a gradient-based method that can robustly extract symmetry axis from visual pattern. The key points of our methods are gradient calculation, symmetric weight calculation, and Hough Transform. Our method was evaluated on several datasets, including both blurred and smooth-edged cases. Experimental results demonstrated that our method achieves a more robust performance than previous methods.
Proc. SPIE. 9812, MIPPR 2015: Automatic Target Recognition and Navigation
KEYWORDS: Signal to noise ratio, Point spread functions, Detection and tracking algorithms, Data modeling, Sensors, Image processing, Particles, Computer simulations, Image filtering, Expectation maximization algorithms
Target cluster brings about a light-spot which consists of several neighborhood pixels in image, therefore it is difficult to distinguish between the targets or locate them with sub-pixel accuracy. In this paper, a pseudo oversampling-based C3PC (Covariance Constrained Constructive Particle Clustering) method is proposed to solve the closely space objects problem. As a classical detection and location method, C3PC algorithm, presents a particle clustering decomposition technique. However, the particle distribution according to the pixel gray value yields pixel level accuracy, which will lead to location error. Thus, by using a particle distribution at sub-pixel level, substantially better position accuracy can be obtained. According the characteristic of oversampling, an improved interpolation algorithm which simulating the oversampling techniques of sensor is brought forward. Simulation experiment results show that the positioning accuracy of CSOs in our algorithm is higher than that of C3PC algorithm.
An effective method for small and dim moving target detection in complicated background is proposed. The proposed approach takes advantage of the Non-local means filter, and applies a novel weight calculation model based on circular mask to the original background estimation pattern. By associating similarity of grayscale distribution of the images with temporal information, the extended method realize the complicated background estimation and point target extraction successfully. To compare existing target detection methods and the proposed method, signal-to-clutter ratio gain (SCRG) and background suppression factor (BSF) are employed for spatial performance comparison and receiver operating characteristics (ROC) is used for detection-performance comparison of the target trajectory. Experimental results demonstrate good performance of the proposed method in complicated scenes and low signal to noise ratio images.
KEYWORDS: 3D acquisition, Target detection, Hough transforms, Signal to noise ratio, Error analysis, Optical engineering, Detection and tracking algorithms, 3D image processing, Tolerancing, Image segmentation
We present a novel Hough transform method for moving point target detection by using a 4-D parameter space. A new representation, which uses four parameters (the distance variable , the angle variable , the velocity variable v, and the distance variable S), is proposed for constant velocity target in the 3-D observation space X-Y-T. By estimating velocity, a target trajectory can be transformed into a 4-D parameter space with a limited range of projection options. Our simulation and analysis show that the new algorithm can produce positive results in suppressing noise points with less computational cost.
This paper presents a new affine registration approach for planar point pattern matching. A process of parameter space
clustering is implemented to confirm a one-to-one mapping between the maximal subsets of feature point sets in images.
For a best performance, a coarse parameter space and a fine parameter space are used for vectors comparison.
Experiments show that the method can produce positive results from a small number of feature points and intensive
We demonstrate a simple configuration for clock recovery from nonreturn-to-zero (NRZ) signal, which is preprocessed
by a narrow-band filter. Clock component is enhanced evidently after the filter. Compared with previous preprocessing
schemes, the single filter is simple and suitable for different bit-rates. The output performances related to the bandwidth
and the detuning of the filter are analyzed. By cascading a clock recovery unit with semiconductor optical amplifier
based fiber ring laser, clock signal can be extracted from the preprocessed signal with extinction ratio over 10 dB and
root mean square timing jitter of 900 fs, at 10 to 40 Gb/s. By simply using a filter with larger bandwidth, much higher
bit-rate operation can be achieved easily.
This paper deals with research on detecting moving point target trajectory in image sequence. A novel method is presents for this purpose, which combines two 2-dimension Hough transforms to suppress noise points and to detect trajectory points in time order. The first Hough transform has an accumulators array using a restricted voting process and a set of straight lines are found in the image plane. A new T-L parameter space is proposed which is derived from these straight lines. In the second transform, collinear points are mapped into T-L space and it is easy to find the direction of motion. Experimental results show that our method can effectively extract moving point target trajectory accurately in a limited observing time especially scanning images from large numbers of noise points while search region is much larger than target movability.
Based on the chirp-pulse compensation technique, a 40-GHz supercontinuum (SC) source generated in a highly nonlinear fiber (HNLF) with large normal dispersion is investigated. We show numerically and experimentally that the widest SC spectrum can be obtained by setting a two-stage all-fiber pulse compressor consisted of the HNLF and standard single-mode fiber (SMF) in front of the last-section HNLF for SC generation. The third dispersion of the fibers, especially the SMF used as chirp-compensating fiber, is found to greatly degrade the SC spectrum generated in this scheme.
Autonomous real-time fingerprint verification, how to judge whether two fingerprints come from the same finger or not, is an important and difficult problem in AFIS (Automated Fingerprint Identification system). In addition to the nonlinear deformation, two fingerprints from the same finger may also be dissimilar due to translation or rotation, all these factors do make the dissimilarities more great and lead to misjudgment, thus the correct verification rate highly depends on the deformation degree. In this paper, we present a new fast simple algorithm for fingerprint matching, derived from the Chang et al.'s method, to solve the problem of optimal matches between two fingerprints under nonlinear deformation. The proposed algorithm uses not only the feature points of fingerprints but also the multiple information of the ridge to reduce the computational complexity in fingerprint verification. Experiments with a number of fingerprint images have shown that this algorithm has higher efficiency than the existing of methods due to the reduced searching operations.
In this paper, a kind of new crystals-Tm,Ho:YVO--have been investigated for the use of 2 micrometers lasers. The absorption and fluorescence spectra of the crystals have been measured to get absorption cross section and effective cross section. The characteristics of these crystals varied with concentration of Tm<SUP>3+</SUP> and Ho<SUP>3+</SUP> were discussed to determine the best conditions in which the crystal can work. The temperature effect of the crystals was measured. All the results are contracted with Tm,Ho:YAG to decide whether this kind of crystals can be used in 2 micrometers lasers.