Complexity and accuracy analysis of common artificial neural networks on pedestrian detection

With the development of computer version, deep learning and artificial neural networks approaches like SPP-net, Faster-RCNN and YOLO are proposed. This paper compares them in terms of efficiency and effectiveness. By analyzing the network architecture, SPP-net is more complex than Faster-RCNN and YOLO. By analyzing the experiments, SPP-net and Faster-RCNN are more accurate than YOLO in static detection while opposite in real-time system. Therefore, in real-time pedestrian detection situation, YOLO can perform better. In static pedestrian detection situation, Faster-RCNN or SPP-net can perform better.

Abstract licence: CC BY

7 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.