In-Vehicle Object Detection in the Wild for Driverless Vehicles

TL;DR

This paper presents a novel approach combining DCGANs and SSD to improve in-vehicle object detection in challenging wild conditions, such as varying illumination and image quality, using real-world taxi videos.

Contribution

The work introduces a GAN-based enhancement integrated with SSD for robust object detection in wild driving conditions, addressing a key challenge in autonomous vehicle perception.

Findings

Significantly improved detection rates in wild conditions

Effective handling of low-quality images in real-world scenarios

Demonstrated success on taxi videos in London during day and night

Abstract

In-vehicle human object identification plays an important role in vision-based automated vehicle driving systems while objects such as pedestrians and vehicles on roads or streets are the primary targets to protect from driverless vehicles. A challenge is the difficulty to detect objects in moving under the wild conditions, while illumination and image quality could drastically vary. In this work, to address this challenge, we exploit Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) to handle with the wild conditions. In our work, a GAN was trained with low-quality images to handle with the challenges arising from the wild conditions in smart cities, while a cascaded SSD is employed as the object detector to perform with the GAN. We used tested our approach under wild conditions using taxi driver videos on London street in both daylight and night times, and the tests from in-vehicle videos demonstrate that this strategy can drastically achieve a better detection rate under the wild conditions.