The paper presents a novel method of image conversion into binary representation. This method of image conversion is based on small orthogonal image gradients. The input image sequence consist of consecutive frames taken from the video stream obtained from the camera placed over a road. Images from the input image sequence are processed separately into binary image representation. Layout of logical values of binary image representation is in accordance with edges of objects comprised in the source image. Vehicle detection is performed by the analysis of changes of the detection field state. The state of the detection field is determined on the basis of appropriate sums of logical values calculated within the detection field. The proposed method of image conversion into binary representation is efficient and attractive computationally. Gradient-based binary image representation is intended for application in road traffic systems. Experimental results are provided.
展开▼
