Triple attention and global reasoning Siamese networks for visual tracking

Pedestrians have random distribution and dynamic characteristics. Aiming to this problem, this paper proposes a pedestrian object detection method based on improved YOLOv5 in urban road scenes. Firstly, the last C3 module was replaced in the Backbone with the SE attention mechanism to enhance the network’s extraction of pedestrian object features and improve the detection accuracy of small-scale pedestrians. Secondly, the EIOU loss function was introduced to optimize the object detection performance of the detection network. To validate the effectiveness of the algorithm, experiments were conducted on a dataset composed of filtered Caltech pedestrian detection data and images taken by ourselves. The experiments showed that the improved algorithm has P-value, R-value, and mAP of 98.4%, 95.5%, and 98%, respectively. Compared to the YOLOv5 model, it has increased P-value by 1.4%, R-value by 2.7%, and mAP by 1.3%. The improved algorithm also boosts the detection speed. The detection speed is 0.8 ms faster than the YOLOv5 model. It is also faster than other mainstream algorithms including Faster R-CNN and SSD. The improved algorithm enhances the effectiveness of pedestrian detection significantly and has important application value.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Triple attention and global reasoning Siamese networks for visual tracking

Cited by 3 publications

References 56 publications

Visual object tracking by using ranking loss and spatial–temporal features

Visual object tracking by using ranking loss and spatial–temporal features

I-VITAL: Information aided visual tracking with adversarial learning

RETRACTED: Research on pedestrian object detection algorithm in urban road scenes based on improved YOLOv5

Contact Info

Product

Resources

About