Accelerated hardware video object segmentation: From foreground detection to connected components labelling

Abstract

This paper demonstrates the use of a single-chip FPGA for the segmentation of moving objects in a video sequence. The system maintains highly accurate background models, and integrates the detection of foreground pixels with the conversion into labelled objects using a connected component labelling algorithm. The background models are based on 24-bit RGB values and 8-bit greyscale intensity values. A multimodal background differencing algorithm is presented, using a single FPGA chip and four blocks of RAM. The realtime connected component labelling algorithm, also designed for FPGA implementation, has efficiently been integrated with the pixel level background subtraction to extract pixels of a moving object as a single blob. The connected component algorithm, run-length encodes the binary image output of the background subtraction, and performs connected component analysis on this representation. The run-length encoding, together with other parts of the algorithm, is performed in parallel; sequential operations are minimized as the number of run-lengths are typically less than the number of pixels.

Stream Processing of Scientific Big Data on Heterogeneous Platforms -- Image Analytics on Big Data in Motion

“…The first step in analytic image processing for many video-based applications is segmentation which is followed by connected-component labeling [10]. Connectedcomponent labeling performs the task of labeling all connected image pixels in a binarized image in order to identify objects or extract certain features of an object.…”

Foreground detection in video streams in an FPGA without external memory

“…Such a formulation is not convenient for an FPGA implementation, namely for high-definition data streams, since each time a separate framebuffer is used in the algorithm, it will increase bandwidth demand on the (external) memory access port (see Figure 1). External framebuffers are often used in image processing applications described in the literature [1], [2], [3]. Using external memory for foreground detection can become a problem in implementations where cost is of primary importance, or where accessing the memory on this low image processing level would interfere with accesses from other (higher) image processing layers.…”

GPU-Accelerated Foreground Segmentation and Labeling for Real-Time Video Surveillance

“…Wang et al [30] applied an adaptive connected component analysis method to remove the small spots of incorrect foreground pixels from the segmentation results of visual background extractor (ViBe). Using a single-chip Field Programmable Gate Array (FPGA) for the segmentation of moving objects in a video, Appiah et al [31] developed a novel feedback background updating method with a CCL algorithm. The moving foreground segmentation and labeling processes were implemented in parallel on the FPGA hardware platform.…”