Moving Object and face detection using FPGA

  • Unique Paper ID: 152556
  • Volume: 8
  • Issue: 3
  • PageNo: 746-753
  • Abstract:
  • Surveillance plays an important role in the present digital world. The advent of new technologies is making the computational process much faster than the existing ones. FPGA implementation of the moving object and face detection enhances the surveillance system by providing the results using the concept of adaptive threshold. The concept of adaptive threshold is used, so that the input comparison is done many times to produce an efficient and clear output. FPGA works at a greater speed (high clock speed) compared to other technologies for implementation. The input images are passed through the Gaussian filter. The HAAR Transform is applied on Gaussian filter’s outputs and considered only LL band for further processing to detect object/face. The modified background subtraction algorithm is applied on LL bands of input images. The adaptive threshold is calculated using LL-band of reference image and object is detected through modified background subtraction algorithm. The detected object is again passed through the second Gaussian filter to get final good quality object. The face detection can be performed using an additional matching unit along with object detection unit. The reference image is replaced by face database images in the face detection. Moving object and face detection system is designed using Xilinx Spartan 6 LX45 FPGA kit. Using FPGA for object and face detection increases the speed of computation and makes the system more efficient. It has applications in various fields such as traffic systems, hospitals, banks

Cite This Article

  • ISSN: 2349-6002
  • Volume: 8
  • Issue: 3
  • PageNo: 746-753

Moving Object and face detection using FPGA

Related Articles