Automatic Pavement Object Detection Using Superpixel Segmentation Combined With Conditional Random Field

Pavement images contain various objects, such as lane-marker, manhole covers, patches, potholes, and curbing. Accurate and robust computer vision algorithms are necessary to detect these various objects that have random shapes, colors, and sizes. In this paper, we have addressed the problem of automatic object detection in pavement images using a unified framework. To detect an object of arbitrary shape in an efficient way, we first divide the image into small consistent regions called superpixels. These superpixels are fast to calculate and preserve object boundaries. We then compute several texture and intensity features within each superpixel. After that, we train support vector machine (SVM) classifier for every feature separately in one-verses-all paradigm. In testing, we first estimate the probability of each superpixel being the part of some object of interest using these SVM classifiers. Since these superpixels' probabilistic scores are independently computed, they do not preserve neighborhood consistency. Therefore, to enforce superpixel neighborhood label consistency, we use contextual optimization technique i.e., conditional random field (CRF). The output of CRF is a pixel-wise binary label map for the objects and background. In addition, due to the lack of any publically available dataset for pavement objects' detection evaluation, we have introduced a new challenging object detection dataset for pavement images. We have performed extensive experiments on this dataset and have obtained encouraging results.