Abstract
With the development of image processing towards deep learning, the detection and tracking technology of ground objects such as vehicles and pedestrians in real scenes is becoming more and more advanced. However, there are still many difficulties in the detection and tracking of multiple objects in real scenes due to the blocking between vehicles and pedestrians and background changes. In this paper, an improved haar-like feature was used in the vehicle and it was compressed. Adaboost classifier was used to detect the feature and Kalman filter was used to track the feature. In combination with the neural network method in pedestrian detection, YOLOv3 network is used to combine deep_sort, and the depth feature is used to fuse LOMO feature for trajectory connection in many complex scenes. The experimental results show that the proposed algorithm reduces training time in vehicle detection and tracking, connects partially disconnected tracks in pedestrian detection and tracking, and improves the integrity of track tracking.
Sign-in/Register to access full text options 
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.
