Vasile Palade, Juliana Negrini de Araujo, Tabassom Sedighi and Alireza Daneshkhah
Adv. Artif. Intell. Mach. Learn., 2 (1):315-337
Vasile Palade : Coventry University
Juliana Negrini de Araujo : Coventry University
Tabassom Sedighi : Anglia Ruskin University
Alireza Daneshkhah : Coventry Univeristy
DOI: https://doi.org/10.54364/AAIML.2022.1121
Article History: Received on: 22-Mar-22, Accepted on: 31-Mar-22, Published on: 31-Mar-22
Corresponding Author: Vasile Palade
Email: ab5839@coventry.ac.uk
Citation: Juliana Negrini de Araujo, Vasile Palade, Tabassom Sedighi, Alireza Daneshkhah (2022). Improving the Pedestrian Detection Performance in the Absence of Rich Training Datasets: A UK Case Study. Adv. Artif. Intell. Mach. Learn., 2 (1 ):315-337
The World Health Organization estimates that well in excess
of one million of lives are lost each year due to road traffic accidents. Since
the human factor is the preeminent cause behind the traffic accidents, the
development of reliable Advanced Driver Assistance Systems (ADASs) and
Autonomous Vehicles (AVs) is seen by many as a possible solution to improve
road safety. ADASs rely on the car perception system input that consists of
camera(s), LIDAR and/or radar to detect pedestrians and other objects on the
road. Hardware improvements as well as advances done in employing Deep Learning
techniques for object detection popularized the Convolutional Neural Networks in
the area of autonomous driving research and applications. However, the
availability of quality and large datasets continues to be a most important
contributor to the Deep Learning based model’s performance. With this in mind,
this work analyses how a YOLO-based object detection architecture responded to
limited data available for training and containing low-quality images. The work
focused on pedestrian detection, since vulnerable road user’s safety is a major
concern within AV and ADAS research communities. The proposed model was trained
and tested on data gathered from Coventry, United Kingdom, city streets. The
results show that the original YOLOv3 implementation reaches a 42.18% average
precision (AP) and the main challenge was in detecting small objects. Network
modifications were made and our final model, based on the original YOLOv3
implementation, achieved 51.6% AP. It is also demonstrated that the employed data
augmentation approach is responsible for doubling the average precision of the
final model.