Detecting real-time objects for traffic surveillance system using single shot detector over CNN with improved accuracy.

Autor:	Vinod, G., Padmapriya, G.
Předmět:	TRAFFIC monitoring OBJECT recognition (Computer vision) CONVOLUTIONAL neural networks DETECTORS VIDEO surveillance
Zdroj:	AIP Conference Proceedings; 2024, Vol. 2729 Issue 1, p1-7, 7p
Abstrakt:	Real-Time Object Detection in traffic surveillance is one of the latest topics in today's world for detecting the objects using Single Shot Detector algorithm over Convolutional Neural Networks. Methods and Materials: Real-Time Object Detection is performed using Single Shot Detector (N=40) over Convolutional Neural Networks (N=40) with the split size of training and testing dataset 70% and 30% respectively. Results: Single Shot Detector has significantly better accuracy (78.9%) compared to Convolutional Neural Networks (47.7%) and attained significance value of p = 0.125. Conclusion: Single Shot Detector achieved significantly better object detection than Convolutional Neural Networks for identifying real-time objects in traffic surveillance. [ABSTRACT FROM AUTHOR]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu