Artificial Intelligence (AI) contributes significantly to the development of autonomous vehicles in an unmatched way. This paper outlines techniques and algorithms for the implementation of Intelligent Autonomous vehicles (IAV) leveraging AI algorithms for traffic perception, decision-making and control in autonomous vehicles through merging traffic scenario detection, traffic lane detection, semantic segmentation, pedestrian detection, and traffic sign classification and detection. The modern computer vision and deep neural networks-based algorithms enable the real-time analysis of different vehicle data through artificial intelligence. The vehicle dynamics are constituted through AI in vehicle control systems for increased safety and efficiency to ensure that they are optimized with time. In addition, the paper will also discuss challenges and possible future directions, underscore how AI has the potential of driving autonomous vehicles towards safer and more reliable as well as intelligent transportation systems. This is the hope of the future whereby mobility is intelligent, sustainable, and accessible with the combination of AI with autonomous vehicles.
Image classification is extensively used in various applications such as satellite imagery, autonomous driving, smartphones, and healthcare. Most of the images used to train classification models can be considered ideal, i.e., without any degradation either due to corruption of pixels in the camera sensors, sudden shake blur, or the compression of images in a specific format. In this paper, we have proposed a novel CNN-based architecture for image classification of degraded images based on intermediate layer knowledge distillation and data augmentation approach cutout named ILIAC. Our approach achieves 1.1%, and 0.4% mean accuracy improvements for all the degradation levels of JPEG and AWGN, respectively, compared to the current state-of-the-art approach. Furthermore, ILIAC method is efficient in computational capacity, i.e., about half the size of the previous state-of-the-art approach in terms of model parameters and GFlops count. Additionally, we demonstrate that we do not necessarily need a larger teacher network in knowledge distillation to improve the model performance and generalization of a smaller student network for the classification of degraded images.