For intelligent transportation systems (ITSs) and planning that makes use of exact location intelligence, accurate vehicle classification, and tracking are topics that are becoming more and more vital. This paper presents a model for the detection and tracking of vehicles in roundabout aerial images. The detection is being done using a combination of blob detection and improved occlusion handling technique based on geometrical points of the vehicle model. The detected vehicles are assigned ID based on IoU matching, similarity matching, and centroid of the vehicle bounding box. The moving cars are then passed onto the tracking algorithm which implements the Kalman filter and vehicle re-identification methods. The trajectories of each detected vehicle are derived. The preciseness of the detection and tracking algorithms are 87% and 90% respectively. The experimental findings showed that the proposed detection and tracking model had consistent results for complex environments having heavy traffic flow conditions.

Vehicle Detection and Tracking Using Kalman Filter Over Aerial Images

Despite recent improvements in computer vision, artificial visual systems’ design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain’s inner workings. Progress in this research area follows the traditional path of hand-made designs using neuroscience knowledge or, more recently, deep learning, a particular branch of machine learning. Recently, a different approach based on genetic programming appeared to enhance handcrafted techniques following two different strategies. The first method follows the idea of combining previous hand-made methods through genetic programming and fuzzy logic. The second approach improves the inner computational structures of basic hand-made models through artificial evolution. This research proposes expanding the artificial dorsal stream using a recent proposal based on symbolic learning to solve salient object detection problems following the second technique. This approach applies the fusion of visual saliency and image segmentation algorithms as a template. The proposed methodology discovers several critical structures in the template through artificial evolution. We present results on a benchmark designed by experts with outstanding results in an extensive comparison with the state of the art, including classical methods and deep learning approaches to highlight the importance of symbolic learning in visual saliency.

/pdf/automated-design-of-salient-object-detection-algorithms-with-ipdiieti.pdf

Automated Design of Salient Object Detection Algorithms with Brain Programming

GNNs (graph neural networks) are deep learning algorithms that operate on graphs. A graph's unique ability to capture structural relationships among data gives insight into more information rather than by analyzing data in isolation. GNNs have numerous applications in different areas, including computer vision. In this chapter, the authors want to investigate the application of graph neural networks (GNNs) to common computer vision problems, specifically on visual saliency, salient object detection, and co-saliency. A thorough overview of numerous visual saliency problems that have been resolved using graph neural networks are studied in this chapter. The different research approaches that used GNN to find saliency and co-saliency between objects are also analyzed. 

Study and Analysis of Visual Saliency Applications Using Graph Neural Networks

For intelligent transportation systems (ITSs) and planning that makes use of exact location intelligence, accurate vehicle classification, and tracking are topics that are becoming more and more vital. This paper presents a model for the detection and tracking of vehicles in roundabout aerial images. The detection is being done using a combination of blob detection and improved occlusion handling technique based on geometrical points of the vehicle model. The detected vehicles are assigned ID based on IoU matching, similarity matching, and centroid of the vehicle bounding box. The moving cars are then passed onto the tracking algorithm which implements the Kalman filter and vehicle re-identification methods. The trajectories of each detected vehicle are derived. The preciseness of the detection and tracking algorithms are 87% and 90% respectively. The experimental findings showed that the proposed detection and tracking model had consistent results for complex environments having heavy traffic flow conditions. 

Abstract Recently, the detection and segmentation of salient objects that attract the attention of human visual in images is determined by using salient object detection (SOD) techniques. As an essential computer vision problem, SOD has increasingly attracted the researchers’ interest over the years. While a lot of SOD models and applications have been proposed, there is still a lack of deep understanding of the issues and achievements. A comprehensive study on the recent techniques of SOD is provided in this paper. Precisely, this paper presents a review of SOD techniques from various perspectives. Various image segmentation techniques are presented such as segmentation based on machine learning or deep learning, the second perspective concentrates on classifying them into supervised and unsupervised learning techniques and the last one based on manual approach, semi-automatic approach, and fully automatic approach and so on. Then, the paper presents a summarization of datasets used for SOD. Finally, analyses of SOD models and comparison results are presented. 

/pdf/performance-evaluation-of-salient-object-detection-2fs9pnr3.pdf

Mai A. Gad

Papers

Performance evaluation of salient object detection techniques