Title :
Real-time detection of line segments using the line Hough transform
Author :
Nagata, Nozomu ; Maruyama, Tsutomu
Author_Institution :
Inst. of Eng. Mech. & Syst., Tsukuba Univ., Japan
Abstract :
We describe a compact circuit for real-time detection of line segments using the line Hough transform (LHT). The LHT is a technique to find out lines in an image. The LHT is robust to noises, but requires long computation time. The circuit calculates: (1) r and θ of lines (r is the distance from the origin to a line and θ is the angle of the line) by the LHT units in parallel; and (2) start and end points of the lines by the other units which are completely pipelined with the LHT units. With this parallel and pipeline processing, the circuit can detect more than 16384 lines (π/512 angle steps) in a large size image (640 × 480) in real-time. The size of the circuit is 19% of XC2V6000, which makes it possible to implement other circuits for higher level processing of object recognition on the same chip, or the performance can be improved up to four times by using four times of the hardware resources.
Keywords :
Hough transforms; digital signal processing chips; edge detection; object recognition; parallel processing; pipeline processing; real-time systems; XC2V6000; image lines; line Hough transform; line segments; object recognition; parallel processing; pipeline processing; real-time detection; Acceleration; Circuit noise; Hardware; Histograms; Image edge detection; Image segmentation; Noise robustness; Object recognition; Pipeline processing; Real time systems;
Conference_Titel :
Field-Programmable Technology, 2004. Proceedings. 2004 IEEE International Conference on
Print_ISBN :
0-7803-8651-5
DOI :
10.1109/FPT.2004.1393255