Accelerated Border Tracking in Binary Images with GPUs

This work presents an optimized algorithm for contour detection and extraction (i.e., border tracking) in binary images, aiming to improve performance in computer vision scenarios that require real-time processing. The proposed method is based on a parallel adaptation of the Suzuki algorithm, widely used in libraries such as OpenCV, but contributes a variant with the advantage of running efficiently on the GPU. The approach divides the image into rectangular blocks, processing each block in parallel to extract “triads” (structures representing three interconnected and ordered points). Subsequently, the triads are connected both within each block and between adjacent blocks to form complete, closed contours. The algorithm is composed of three stages, each implemented as CUDA kernels. The main goal of the proposed algorithm is to avoid costly data transfers between the CPU and GPU, which is especially beneficial when the algorithm is part of industrial workflows with high efficiency requirements.