Driver fatigue is one of the main causes of frequent traffic accidents. In this case, driver fatigue detection system has very important significance in avoiding traffic accidents. This paper presents a real-time method based on fusion of multiple facial features, including eye closure, yawn and head movement. The eye state is classified as being open or closed by a linear SVM classifier trained using HOG features of the detected eye. The mouth state is determined according to the width-height ratio of the mouth. The head movement is detected by head pitch angle calculated by facial landmark. The driver’s fatigue state can be reasoned by the model trained by above features. According to experimental results, drive fatigue detection obtains an excellent performance. It indicates that the developed method is valuable for the application of avoiding traffic accidents caused by driver’s fatigue.
Aiming at the problem that the correlation filter-based tracking algorithm can not track the target of severe occlusion, a target re-detection mechanism is proposed. First of all, based on the ECO, we propose the multi-peak detection model and the response value to distinguish the occlusion and deformation in the target tracking, which improve the success rate of tracking. And then we add the confidence model to update the mechanism to effectively prevent the model offset problem which due to similar targets or background during the tracking process. Finally, the redetection mechanism of the target is added, and the relocation is performed after the target is lost, which increases the accuracy of the target positioning. The experimental results demonstrate that the proposed tracker performs favorably against state-of-the-art methods in terms of robustness and accuracy.
Airplane detection in remote sensing images remains a challenging problem and has also been taking a great interest to researchers. In this paper we propose an effective method to detect airplanes in remote sensing images using convolutional neural networks. Deep learning methods show greater advantages than the traditional methods with the rise of deep neural networks in target detection, and we give an explanation why this happens. To improve the performance on detection of airplane, we combine a region proposal algorithm with convolutional neural networks. And in the training phase, we divide the background into multi classes rather than one class, which can reduce false alarms. Our experimental results show that the proposed method is effective and robust in detecting airplane.
Facial expression recognition is a currently active research topic in the fields of computer vision, pattern recognition and artificial intelligence. In this paper, we have developed a convolutional neural networks (CNN) for classifying human emotions from static facial expression into one of the seven facial emotion categories. We pre-train our CNN model on the combined FER2013 dataset formed by train, validation and test set and fine-tune on the extended Cohn-Kanade database. In order to reduce the overfitting of the models, we utilized different techniques including dropout and batch normalization in addition to data augmentation. According to the experimental result, our CNN model has excellent classification performance and robustness for facial expression recognition.
This paper presents a street rubbish detection algorithm based on image registration with Sift feature and RCNN. Firstly, obtain the rubbish region proposal on the real-time street image and set up the CNN convolution neural network trained by the rubbish samples set consists of rubbish and non-rubbish images; Secondly, for every clean street image, obtain the Sift feature and do image registration with the real-time street image to obtain the differential image, the differential image filters a lot of background information, obtain the rubbish region proposal rect where the rubbish may appear on the differential image by the selective search algorithm. Then, the CNN model is used to detect the image pixel data in each of the region proposal on the real-time street image. According to the output vector of the CNN, it is judged whether the rubbish is in the region proposal or not. If it is rubbish, the region proposal on the real-time street image is marked. This algorithm avoids the large number of false detection caused by the detection on the whole image because the CNN is used to identify the image only in the region proposal on the real-time street image that may appear rubbish. Different from the traditional object detection algorithm based on the region proposal, the region proposal is obtained on the differential image not whole real-time street image, and the number of the invalid region proposal is greatly reduced. The algorithm has the high mean average precision (mAP).
The algorithm of single image haze removal using dark channel prior has a good result on restoring hazy images and makes it clear. But the original algorithm has some disadvantages such as inaccurate estimation of atmospheric light and distortion of the sky region. From the perspective of the two problems referred previously, we propose a new method to estimate the transmission and atmosphere light. First, according to the characteristics of the sky region, we divide the sky region and get the accurate atmospheric light; then, in order to avoid the distortion of the sky, a controllable parameter K is introduced to the transmission. The experiment results show that the restored images acquired by the experiment have natural colors and clear details.
Infrared medical examination finds the diseases through scanning the overall human body temperature and obtaining the temperature anomalies of the corresponding parts with the infrared thermal equipment. In order to obtain the temperature anomalies and disease parts, Infrared Medical Image Visualization and Anomalies Analysis Method is proposed in this paper. Firstly, visualize the original data into a single channel gray image: secondly, turn the normalized gray image into a pseudo color image; thirdly, a method of background segmentation is taken to filter out background noise; fourthly, cluster those special pixels with the breadth-first search algorithm; lastly, mark the regions of the temperature anomalies or disease parts. The test is shown that it’s an efficient and accurate way to intuitively analyze and diagnose body disease parts through the temperature anomalies.
In recent years, the occurrence of large earthquakes is frequent all over the word. In the face of the inevitable natural disasters, the prediction of the earthquake is particularly important to avoid more loss of life and property. Many achievements in the field of predict earthquake from remote sensing images have been obtained in the last few decades. But the traditional prediction methods presented do have the limitations of can't forecast epicenter location accurately and automatically. In order to solve the problem, a new predicting earthquakes method based on extract the texture and emergence frequency of the earthquake cloud is proposed in this paper. First, strengthen the infrared cloud images. Second, extract the texture feature vector of each pixel. Then, classified those pixels and converted to several small suspected area. Finally, tracking the suspected area and estimate the possible location. The inversion experiment of Ludian earthquake show that this approach can forecast the seismic center feasible and accurately.
Cloud is floating in the earth sky widely, irregularly and frequently. So it appears in the satellite imagery. The cloud in
the remote sensing imagery especially high resolution remote sensing imagery and aerial image will largely reduce the
remote sensing image quality and use ratio, hinder the further application and the subsequent processing. Cloud detection
accurately is a necessary and important step in the remote sensing image data analysis processing. So, a new cloud
detection method based on HSI color space and stationary wavelet transformation (SWT) according to the spectral
properties of cloud and the different with other objects is proposed in this paper. First, transform the RGB to HSI of
image; then SWT is implemented to achieve the low frequency; the last result of cloud detection is obtained by the
segmentation and edge extraction use SOBLE. The experiments show that the approach can detect the cloud accurately,
availably and quickly.
A communication system of the smart grid based on the partial reconfiguration technology was provided dependent on the analysis of the principle and the requirements of the smart grid. The system can dynamically update the smart grid protocol and interface design during normal operating in order to avoid unnecessary outage. While the use of the partial reconfiguration technology reduces the occupation rate of the FPGA resource, increase the flexibility of the system, and decrease the research the design time for the system. Moreover, the general architecture based on the partial reconfiguration technology can be used in various remote control device of the smart grid.
Shadow is one of the basic characteristics in urban remote sensed imagery. It affects the extraction of object’s edge, identification of objects and registration of images, so shadow detection has a great importance in urban remote sensing. In this paper, a kind of method with HSV is proposed to detect shadow from the color high resolution remote sensing imagery mainly through a series of processing steps including twice HSV transformation, self-adaptive segmentation, morphological closing operation and little area removing. At last, the ratio of the shadow is achieved according to the shadow area statistical analysis. The experiments show that the approach can detect the shadow accurately and availably.
The building recognition from high resolution remote sensing images is an internationally advanced research field. But
there are still many difficult to be solved. In this paper, in order to extract and recognize the special building from the
high resolution remote sensing images, a new algorithm is presented. First, a self-adaptive Average Absolute Difference
Maximum edge enhancement algorithm is presented to enhance the edge of the building and suppress the background at
one time. Second, the locally self-adaptive segmentation algorithm is implemented to obtain the binary image. Third, the
thinning algorithm is implanted to obtain the single pixel edge of the building and a pruning algorithm is necessary in
order to reduce the computation times in the following process. The following step is obtained by the Hough
transformation to make the edge of the building into polygon. Finally, an Interior angle chain (IAC) is proposed to
recognize the building with different shape. The experimental results demonstrate that the new algorithm can extract the
special shape building quickly and accurately.
Image mosaic technology is an important research field of image processing and a research focus on the computer vision
and computer graphics. The traditional method is to select the feature points by manual selection method, which faces
the problem of low reliability and efficiency in the batch of the image mosaic. The SIFT features have many properties
that make them suitable for matching differing images of an object or scene. But the computation amount and the
computation complexity are so great, which restricts the further real time application. So an automatic remote sensing
image mosaic algorithm based on modified SIFT feature is presented in this paper to solve these problems. The method
presented in this paper consisted of three steps: noise removal, modified SIFT feature registration and automatic mosaic.
The test results show the modified mosaic algorithm based on the SIFT feature can improve the matching accuracy and
reduce the computation times.
The development of the remote sensing technology makes us obtain very abundant information of nature, especially
with the appearance of high resolution remote sensing image it extends the visual field of the nature. High-resolution
satellite images such as Quickbird and IKONOS have been applied into many fields. But the challenge that faces us is
how to make use of the data effectively and obtain more useful information through some processing. Because in the
target recognition, the mutual-complementarity among the different results obtained by the different classifier making
using of the same features usually is very strong and high resolution remote sensing data have a lot of characteristics
such as spectral, texture and context and so on compared to the other lower resolution remote sensing data, the Multiple
Classifiers making use of multi-characteristic was proposed to improve the high resolution remote sensing image
classification accuracy in this paper. The experiments show that the approach can obtain higher classification accuracy
and better classification result than single classifier.