Enhanced Multi-Task Learning Architecture for Detecting Pedestrian at Far Distance

• Published in: IEEE transactions on intelligent transportation systems Vol. 23; no. 9; pp. 15588 - 15604
• Main Authors: Zhou, Chengju, Wu, Meiqing, Lam, Siew-Kei
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-09-2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Annotations; cascade detection; Computational complexity; Feature extraction; Head; Image segmentation; Multi-task learning; Multitasking; pedestrian detection; Pedestrians; Performance degradation; Proposals; Semantic segmentation; Semantics
• DOI: 10.1109/TITS.2022.3142445
• EISSN: 1558-0016
• ISSN: 1524-9050

Existing pedestrian detection methods suffer from performance degradation in the presence of small-scale pedestrians who are positioned at far distance from the camera. We present a pedestrian detection framework that is not only robust to small- and large-scale pedestrians, but is also significantly faster than state-of-the-art methods. The proposed framework incorporates semantic segmentation to confidence modules for RPN (Region Proposal Network) head and R-FCN (Region-based Fully Convolutional Networks) head, and a cascaded R-FCN head. The semantic segmentation confidence is extracted and utilized as auxiliary classification prior knowledge for RPN proposal selection and R-FCN head prediction. Finally, the cascaded R-FCN head progressively refine the pedestrian prediction accuracy with negligible computation overhead. The proposed framework is also capable of maintaining high detection performance on down-sampled input images, which leads to further reduction in overall computational complexity. Experiment results on CityPersons and MOT17Det datasets show that the proposed framework achieves competitive detection performance with about <inline-formula> <tex-math notation="LaTeX">3\times </tex-math></inline-formula> speedup over state-of-the-art methods.