Failure in pedestrian detection systems can be extremely crucial, specifically in driverless driving. In this paper, failures in pedestrian detectors are refined by re-evaluating the results of state of the art pedestrian detection systems, via a fully convolutional neural network. The network is trained on a number of datasets which include a custom designed occluded pedestrian dataset to address the problem of occlusion. Results show that when applying the proposed network, detectors can not only maintain their state of the art performance, but they even decrease average false positives rate per image, especially in the case where pedestrians are occluded.
|Konference||The 11th International Conference on Machine Vision|
|Periode||01/11/2018 → 03/11/2018|
|Navn||Proceedings of SPIE, the International Society for Optical Engineering|