Infrared pedestrian detection systems struggle with real-time processing performance. Known solutions are limited to either low resolution systems with basic functionality running at full frame rate, or software based techniques featuring higher detection rates with full set of features, however running only in off-line mode for statistical analysis. Here, a comprehensive solution for real-time pedestrian detection is described. This research project includes investigation of possible solutions, design, development and implementation of a pedestrian detection system, processing data from infrared video source in real-time. Design requirements include processing at full frame rate as well as low memory and system resource consumption. The memory utilization is one of the major concerns since high demand for memory resources is a critical aspect in most image processing applications. For the purpose of this task, a number of general purpose image processing techniques were revised, taking into consideration the suitability for infrared pedestrian detection. These tasks include background separation, acquisition noise removal and object detection through connected component labelling. They are discussed and addressed in individual chapters. Various techniques for background segmentation are discussed. A chronological review of popular techniques is provided. The proposed architecture for background subtraction is based on selective running average for adaptive background model, supported by adaptive thresholding based on histogram calculation. In order to remove acquisition noise, a dual decomposed architecture was introduced, based on mathematical morphology and basic set theory de�nitions. It includes both erosion and dilation performed in a pipeline. For the purpose of object detection and feature extraction, a connected component labelling technique was employed, based on a single pass approach to ful�l real-time processing requirement. The system was implemented, veri�ed and tested on XUP FPGA Development Board with Virtex-II Pro XC2VP30 chip from Xilinx. Details and limitation of the speci�c implementation are discussed. An overview of experimental pedestrian detection results is provided. The thesis concludes with system analysis and suggestions for future work.

This paper describes a Hardware Description Language (HDL) based fully customizable module for real-time Infrared (IR) hot spot detection and feature extraction from a video stream. The aim of the research was to investigate and evaluate possible solutions for object detection using connected component labelling that could be implemented within a streaming video embedded processing platform as a hardware accelerator. The proposed algorithm is based on a single-pass approach; this guarantees real-time processing together with very low resource utilisation. The hardware implementation was verified on a Xilinx XUP V2P (XC2VP30 FPGA) development board with an IR camera module interfaced as a real-time video source. The system was tested with an image resolution of 640 × 480 processing input data at a speed of 30fps which was limited by the bandwidth of the camera.

The objective of this paper is to carry out a detailed analysis of the most popular connected components labeling (CCL) algorithms for binary images. This study investigates their usability for processing streaming data and suitability for implementation using Field-Programmable Gate Array (FPGA) devices. The first part of this paper presents the state of the art on CCL algorithms. Both capability for real-time video processing as well as memory requirements are taken into consideration. The second part of the paper describes an efficient implementation of the single pass labeling algorithm using a Virtex-II Pro FPGA. It is verified on the development board with an infrared camera module as a real-time video source. The system is capable of processing video stream with 640 x 480 pixels per frame at a speed of 30 fps limited by the bandwidth of the video source.

An FPGA-based implementation of a pedestrian detection system using thermal infrared imaging is presented. The main feature of the processing platform is its ability to detect pedestrians at frame-rate from an infrared video stream. It is designed as a stand alone processing unit, supporting security systems in low visibility conditions. The processing unit digitizes a video source from a thermal infrared camera and after preprocessing, provides features of the detected pedestrians such as their position, height and width to a host computer where visualization of tracking and statistical operations can be applied to the received data. The data is transmitted to the host PC via a Bluetooth module interfaced to the development board. The wireless communication allows also for remote control of the processing system's configuration registers. At the present stage of evaluation, the processing unit is limited to detect and transmit the coordinates of one pedestrian in a video frame. The system was implemented using a Xilinx Virtex-II Pro XC2VP30 FPGA chip, no additional memory is required.