ATG-PVD: Ticketing Parking Violations on A Drone

TL;DR

This paper presents ATG-PVD, a drone-embedded framework for automated parking violation detection combining novel CNNs for optical flow and car detection, verified through real-world drone experiments.

Contribution

Introduces a novel suspect-and-investigate framework with specialized CNNs for optical flow and car detection, embedded in a drone for parking violation detection.

Findings

SwiftFlow outperforms state-of-the-art optical flow methods in speed and accuracy

Flow-RCNN detects illegally parked cars more effectively than Faster-RCNN

Investigation module successfully verifies parking violations after drone re-localization

Abstract

In this paper, we introduce a novel suspect-and-investigate framework, which can be easily embedded in a drone for automated parking violation detection (PVD). Our proposed framework consists of: 1) SwiftFlow, an efficient and accurate convolutional neural network (CNN) for unsupervised optical flow estimation; 2) Flow-RCNN, a flow-guided CNN for car detection and classification; and 3) an illegally parked car (IPC) candidate investigation module developed based on visual SLAM. The proposed framework was successfully embedded in a drone from ATG Robotics. The experimental results demonstrate that, firstly, our proposed SwiftFlow outperforms all other state-of-the-art unsupervised optical flow estimation approaches in terms of both speed and accuracy; secondly, IPC candidates can be effectively and efficiently detected by our proposed Flow-RCNN, with a better performance than our baseline network, Faster-RCNN; finally, the actual IPCs can be successfully verified by our investigation module after drone re-localization.