Abstract
Vehicle detection is involved in a wide range of intelligent transportation and smart city applications, and the demand of fast and accurate detection of vehicles is increasing. In this article, we propose a convolutional neural network-based framework, called separable reverse connected network, for multi-scale vehicles detection. In this network, reverse connected structure enriches the semantic context information of previous layers, while separable convolution is introduced for sparse representation of heavy feature maps generated from subnetworks. Further, we use multi-scale training scheme, online hard example mining, and model compression technique to accelerate the training process as well as reduce the parameters. Experimental results on Pascal Visual Object Classes (VOC) 2007 + 2012 and MicroSoft Common Objects in COntext (MS COCO) 2014 demonstrate the proposed method yields state-of-the-art performance. Moreover, by separable convolution and model compression, the network of two-stage detector is accelerated by about two times with little loss of detection accuracy.
Highlights
Vehicle detection is one of the essential tasks in surveillance systems, driver-assistance systems, and a wide range of intelligent transportation and smart city applications
By separable convolution (SC) and model compression, the network of two-stage detector is accelerated by about two times with little loss of detection accuracy
For comparison of different vehicle detectors based on convolutional neural network (CNN), we conduct a series of comparative experiments for evaluating the performances of existing frameworks as well as the proposed separable reverse connected (SRC) method using the same image data sets and training schemes
Summary
Vehicle detection is one of the essential tasks in surveillance systems, driver-assistance systems, and a wide range of intelligent transportation and smart city applications. Vision-based vehicle detection systems should be robust, fast, and accurate so as to deal with different situation. Many efforts have been devoted to design methods and systems, yet the detection accuracy and speed are still unsatisfactory in real-world applications. Due to the limited representation and discrimination ability of handcrafted features, such methods can hardly provide sufficient accuracy for detection in complex scenes. In 2012, Krizhevsky et al.[6] proposed a deep convolutional neural network (CNN) which achieved recordbreaking image classification accuracy in the large scale recognition challenge. With the rapid progress of CNN in recent years, CNNbased vehicle detectors have achieved remarkable performance and become dominant in detection tasks. CNN and deep learning-based detectors still cannot meet the demands in real applications, in the respects below
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
