Focal Loss Dense Detector for Vehicle Surveillance

TL;DR

This paper introduces a focal loss-based RetinaNet for vehicle detection that achieves a balance of high speed and accuracy, outperforming traditional two-stage detectors on the DETRAC dataset.

Contribution

It presents a novel application of focal loss in RetinaNet to enhance one-stage detector accuracy for vehicle surveillance.

Findings

Achieves state-of-the-art accuracy on DETRAC dataset.

Balances speed and detection performance effectively.

Outperforms traditional two-stage detectors in vehicle detection.

Abstract

Deep learning has been widely recognized as a promising approach in different computer vision applications. Specifically, one-stage object detector and two-stage object detector are regarded as the most important two groups of Convolutional Neural Network based object detection methods. One-stage object detector could usually outperform two-stage object detector in speed; However, it normally trails in detection accuracy, compared with two-stage object detectors. In this study, focal loss based RetinaNet, which works as one-stage object detector, is utilized to be able to well match the speed of regular one-stage detectors and also defeat two-stage detectors in accuracy, for vehicle detection. State-of-the-art performance result has been showed on the DETRAC vehicle dataset.