In order to reduce the traffic accidents caused by driver fatigue, this paper extends the TLD tracking algorithm to the case of detecting and tracking driver's face and local areas which is based on the machine vi...
详细信息
ISBN:
(纸本)9783662483862;9783662483848
In order to reduce the traffic accidents caused by driver fatigue, this paper extends the TLD tracking algorithm to the case of detecting and tracking driver's face and local areas which is based on the machine vision. We address problems of detecting driver's face and local areas, which contain the driver's fatigue information, via adaboost cascade classifier based on haar-like features and track the target areas by the TLD method. The main results are given in terms of the accuracy of detecting driver's face and local areas. Lay a foundation for the driver fatigue detection.
The paper is devoted to the problem of real-time pedestrian recognition on mobile phones. The insufficient quality of conventional detection methods is highlighted. We propose here a specialized procedure of data gath...
详细信息
ISBN:
(纸本)9783319296081;9783319296067
The paper is devoted to the problem of real-time pedestrian recognition on mobile phones. The insufficient quality of conventional detection methods is highlighted. We propose here a specialized procedure of data gathering and preprocessing to train cascadeclassifiers. Firstly, automobile video recorder is used to get real pedestrian images. Secondly, the application for training sample preprocessing is designed to prepare positives and negatives by image cutting. Experimental results in testing under real road conditions with several mobile phones reveal that the best quality (3% of false positives and 19% of false negatives rate) is achieved with the Haar features. In conclusion we emphasized that sometimes it is necessary to choose faster, but less accurate, object detection algorithm, because in this case it is possible to process more number of frames in a fixed period of time. Hence, the total object detection accuracy can be increased.
In this paper a moving vehicle detection algorithm based on visual processing mechanism with multiple pathways is proposed, in which the multiple pathways visual processing mechanism is inspired by the biological visu...
详细信息
ISBN:
(纸本)9783319220536;9783319220529
In this paper a moving vehicle detection algorithm based on visual processing mechanism with multiple pathways is proposed, in which the multiple pathways visual processing mechanism is inspired by the biological visual system. According to the different moving directions of front vehicles, orientation selectivity of visual cortex cells is used to construct a visual processing model with three pathways. In each pathway, an adaboost cascade classifier is trained using a set of special samples for detection of moving vehicles. The adaboost cascade classifier is response to multi-block local binary patterns (MB-LBP) of vehicles. The experimental results show that the multiple pathways visual processing mechanism, compared with the single pathway adaboost cascade classifier and the conventional method, not only can reduce the complexity of the classifier and training time, but also can improve the recognition rate of moving vehicle.
Traditional manual fiber defect detection is inefficient and imprecise when the fiber moves fast, to solve the problem, a real-time optical fiber defect detection system based on machine vision is designed and develop...
详细信息
ISBN:
(纸本)9781479958252
Traditional manual fiber defect detection is inefficient and imprecise when the fiber moves fast, to solve the problem, a real-time optical fiber defect detection system based on machine vision is designed and developed. Detection system by three industrial cameras captures images of 0 degrees,120 degrees,240 degrees angle in space which are transmitted to IPC to classify fiber defect. Fiber defects are defined to establish classification database and criterion. Common adaboostclassifier is effective for this problem but wastes too much time, so an advanced adaboost cascade classifier based on morphological characteristics is designed. Detection results under industry condition show that the system meets the requirement of real-time detection and has high detecting accuracy of more than 99%.
This paper proposed a robust framework of detecting the real-time queuing and dissipation of a vehicle queue by two cameras, one fixed at the front of the stop line and the other somewhere behind the stop line, jointl...
详细信息
ISBN:
(纸本)9781457721977
This paper proposed a robust framework of detecting the real-time queuing and dissipation of a vehicle queue by two cameras, one fixed at the front of the stop line and the other somewhere behind the stop line, jointly monitoring the interested region with opposite and long-range views. Firstly, the position changes of the tail and head of a vehicle queue, which accurately describe the formation and dissipation of the queue, can be efficiently tracked in each camera at intersection during morning and evening rush hours, with a duplex flexible window fused with the Haar feature based adaboost cascade classifiers. Secondly, the data of these two cameras in this large-area outdoor traffic application are fused at decision level to improve the accuracy of the tracking, according to the tracking result in each camera. Then, the queue length and stop delay of vehicles can be calculated readily. Experiments show that the proposed method can detect the formation and dissipation of the queue under varying illumination in real time, and that the accuracy rate is about 90.24%. Therefore, this method can be further applied to traffic congestion monitoring and traffic signal controlling.
暂无评论