Evaluation of Non-Classical Decision-Making Methods in Self Driving Cars: Pedestrian Detection Testing on Cluster of Images with Different Luminance Conditions

Abstract

Self-driving cars, i.e., fully automated cars, will spread in the upcoming two decades, according to the representatives of automotive industries; owing to technological breakthroughs in the fourth industrial revolution, as the introduction of deep learning has completely changed the concept of automation. There is considerable research being conducted regarding object detection systems, for instance, lane, pedestrian, or signal detection. This paper specifically focuses on pedestrian detection while the car is moving on the road, where speed and environmental conditions affect visibility. To explore the environmental conditions, a pedestrian custom dataset based on Common Object in Context (COCO) is used. The images are manipulated with the inverse gamma correction method, in which pixel values are changed to make a sequence of bright and dark images. The gamma correction method is directly related to luminance intensity. This paper presents a flexible, simple detection system called Mask R-CNN, which works on top of the Faster R-CNN (Region Based Convolutional Neural Network) model. Mask R-CNN uses one extra feature instance segmentation in addition to two available features in the Faster R-CNN, called object recognition. The performance of the Mask R-CNN models is checked by using different Convolutional Neural Network (CNN) models as a backbone. This approach might help future work, especially when dealing with different lighting conditions.

Impact of Traffic Sign Diversity on Autonomous Vehicles

“…Although 2.17% of failed alarms are due to the weakness of this approach in noise and occlusions, this method can detect 95.65% of sign shapes from the dataset consisting of 48 images per a resolution of 360 × 270 pixels covering three various traffic signs. Junaid et al (2021) Focused on Mask R-CNN to detect objects (pedestrians) while the vehicle is traveling on the road, and for image manipulation, the inverse gamma correction method was used, which is directly related to the intensity of illumination. Six backbone models of Mask R-CNN were tested on the Penn-Fudan database in the process of feature extraction and bounding box identification.…”

“…6 The proposed detection approach (Behloul and Saadna, 2014) Fig. 7 Different Mask R-CNN model results applied on adapted from (Junaid et al, 2021) to a fully connected final layer with six neurons to achieve classification. 3.…”

Reducing Model Complexity in Neural Networks by Using Pyramid Training Approaches

“…In the rapidly evolving field of machine learning, Convolutional Neural Networks (CNNs) are extensively used for visual information processing, playing pivotal roles in areas such as image classification [1,2], object detection [3,4], facial recognition [5], medical imaging [6,7], and autonomous driving [8]. As these tasks grow in complexity, so too do the models designed to tackle them, often resulting in increased model size and computational demands.…”

Advances in Automated Driving Systems

“…Improvement of vehicle control for wheel loaders was investigated in [10] using a deep learning-based prediction model of the throttle valve. The difficulties in reliable detection of pedestrians is addressed in [11], based on convolutional neural network algorithms applied on images manipulated with inverse gamma correction. Vehicle control at handling limits was investigated in [12], introducing a model-predictive controller that is able to initiate and maintain steadystate drifting.…”