Disparity Image Segmentation For ADAS
This work addresses segmentation for advanced driver-assistance systems, but it is incremental as it adapts existing methods to a specific domain.
The paper tackled the problem of segmenting grayscale disparity images for ADAS by customizing Connected Component Labeling algorithms for region growing and merging, achieving efficient implementation on embedded automotive hardware with results demonstrated on standard datasets like Tsukuba stereo-pair.
We present a simple solution for segmenting grayscale images using existing Connected Component Labeling (CCL) algorithms (which are generally applied to binary images), which was efficient enough to be implemented in a constrained (embedded automotive) architecture. Our solution customizes the region growing and merging approach, and is primarily targeted for stereoscopic disparity images where nearer objects carry more relevance. We provide results from a standard OpenCV implementation for some basic cases and an image from the Tsukuba stereo-pair dataset.