Deep Learning based Pedestrian Detection at Distance in Smart Cities

TL;DR

This paper introduces a novel GAN-based architecture with a cascaded SSD for improved pedestrian detection at distance in smart city videos, addressing low-resolution challenges and multi-scale object recognition.

Contribution

It proposes a new GAN-augmented detection framework that enhances resolution and discriminative features for better distant pedestrian detection.

Findings

Achieved higher detection rates for distant pedestrians and vehicles.

Demonstrated effectiveness on CIFAR dataset with improved accuracy.

Suitable for real-time smart city applications.

Abstract

Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test. In this paper, we leveraged GANs and proposed a new architecture with a cascaded Single Shot Detector (SSD) for pedestrian detection at distance, which is yet a challenge due to the varied sizes of pedestrians in videos at distance. To overcome the low-resolution issues in pedestrian detection at distance, DCGAN is employed to improve the resolution first to reconstruct more discriminative features for a SSD to detect objects in images or videos. A crucial advantage of our method is that it learns a multi-scale metric to distinguish multiple objects at different distances under one image, while DCGAN serves as an encoder-decoder platform to generate parts of an image that contain better discriminative information. To measure the effectiveness of our proposed method, experiments were carried out on the Canadian Institute for Advanced Research (CIFAR) dataset, and it was demonstrated that the proposed new architecture achieved a much better detection rate, particularly on vehicles and pedestrians at distance, making it highly suitable for smart cities applications that need to discover key objects or pedestrians at distance.