This paper introduces a real-time Vehicle Collision Avoidance System (V-CAS) designed to enhance vehicle safety through adaptive braking based on environmental perception. V-CAS leverages the advanced vision-based transformer model RT-DETR, DeepSORT tracking, speed estimation, brake light detection, and an adaptive braking mechanism. It computes a composite collision risk score based on vehicles' relative accelerations, distances, and detected braking actions, using brake light signals and trajectory data from multiple camera streams to improve scene perception. Implemented on the Jetson Orin Nano, V-CAS enables real-time collision risk assessment and proactive mitigation through adaptive braking. A comprehensive training process was conducted on various datasets for comparative analysis, followed by fine-tuning the selected object detection model using transfer learning. The system's effectiveness was rigorously evaluated on the Car Crash Dataset (CCD) from YouTube and through real-time experiments, achieving over 98% accuracy with an average proactive alert time of 1.13 seconds. Results indicate significant improvements in object detection and tracking, enhancing collision avoidance compared to traditional single-camera methods. This research demonstrates the potential of low-cost, multi-camera embedded vision transformer systems to advance automotive safety through enhanced environmental perception and proactive collision avoidance mechanisms.

Surveillance cameras plays an essential role in securing our home or business. These cameras are super affordable. So is setting up a surveillance system. The only difficult and expensive part is the monitoring. For real time monitoring, usually a security personnel or a team has to be assigned. It is simply not feasible for all.

The device used in this work detects the objects over the surface of the water using two thermal cameras which aid the users to detect and avoid the objects in scenarios where the human eyes cannot (night, fog, etc.). To avoid the obstacle collision autonomously, it is required to track the objects in real-time and assign a specific identity to each object to determine its dynamics (trajectory, velocity, etc.) for making estimated collision predictions. In the following work, a Machine Learning (ML) approach for Computer Vision (CV) called Convolutional Neural Network (CNN) was used using TensorFlow as the high-level programming environment in Python. To validate the algorithm a test set was generated using an annotation tool that was created during the work for proper evaluation. Once validated, the algorithm was deployed on the platform and tested with the sequence generated by the test boat.

DeepSort is a machine learning model for tracking people, assigning IDs to each person. Traditionally, tracking has used an algorithm called Sort (Simple Online and Realtime Tracking), which uses the Kalman filter. Using the bounding boxes detected by YOLO v3, we can assign an ID and track a person by mapping bounding boxes of similar size and similar motion in previous and following frame. However, Sort presents the limitation that if a person hid behind an object and then reappeared, it is assigned a different ID. DeepSort solves this problem by using an AI model that compares similarity between people, thus reducing the issue of switching people's identities.