#

High Speed Target Tracking

using Self Windowing

Self windowing is a simple target extraction algorithm that works by
calculating the logical AND of the input image and the dilated image
of the target calculated on the previous frame. It takes advantage of the high-speed
nature of the processing: all the pixels of the new target image falls within the
1-pixel dilated image of the previous estimated target. Let the input image be f_{k}(i,j) at time k, and the
target image be g_{k}(i,j), and we describe the algorithm as
following ("|","&" are OR, AND operaration respectively).

**
g**_{k+1}(i,j) = ( g_{k}(i,j) |
g_{k}(i+1,j) | g_{k}(i-1,j) | g_{k}(i,j+1) |
g_{k}(i,j-1)) & f_{k+1}(i,j)

We realized target tracking considering collision and separation
between a target object and its environment using the algorithm on
1ms visual feedback system. Now target extraction by self windowing,
collision detection and separation detection require
300us(23steps), 480us(1 summation calculation) and 1.7ms(3 summation
calculations and 20 steps) respectively, and this combination requires
2.5ms(4 summation calculation and 43 steps). In future using high
speed summation calculation circuits, such as a resistive network,
the algorithm will be executed more quickly.

Movies (MPEG format1.5Mbytes)
### Reference

- Idaku Ishii, Yoshihiro Nakabo, and Masatoshi Ishikawa: Target
Tracking Algorithm for 1ms Visual Feedback System Using Massively
Parallel Processing, IEEE Int. Conf. Robotics and Automation
(Minneapolis, 1996.4.25)/Proc. IEEE Int. Conf. Robotics and
Automation, pp.2309-2314

[Home|
Sensor Fusion|
DVS|
Vision Chip|
Meta Perception|
Members|
Papers|
Movies]

Ishikawa Nami Komuro laboratory WWW admin:
www-admin@k2.t.u-tokyo.ac.jp