Bringing Generalization to Deep Multi-View Pedestrian Detection

24 Sep 2021  ·  Jeet Vora, Swetanjal Dutta, Kanishk Jain, Shyamgopal Karthik, Vineet Gandhi ·

Multi-view Detection (MVD) is highly effective for occlusion reasoning in a crowded environment. While recent works using deep learning have made significant advances in the field, they have overlooked the generalization aspect, which makes them impractical for real-world deployment. The key novelty of our work is to formalize three critical forms of generalization and propose experiments to evaluate them: generalization with i) a varying number of cameras, ii) varying camera positions, and finally, iii) to new scenes. We find that existing state-of-the-art models show poor generalization by overfitting to a single scene and camera configuration. To address the concerns: (a) we propose a novel Generalized MVD (GMVD) dataset, assimilating diverse scenes with changing daytime, camera configurations, varying number of cameras, and (b) we discuss the properties essential to bring generalization to MVD and propose a barebones model to incorporate them. We perform a comprehensive set of experiments on the WildTrack, MultiViewX, and the GMVD datasets to motivate the necessity to evaluate the generalization abilities of MVD methods and to demonstrate the efficacy of the proposed approach. The code and the proposed dataset can be found at https://github.com/jeetv/GMVD

PDF Abstract

Datasets


Introduced in the Paper:

GMVD

Used in the Paper:

Wildtrack MultiviewX

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multiview Detection GMVD GMVD MODA 68.2 # 2
Recall 75.5 # 2

Methods


No methods listed for this paper. Add relevant methods here