Moving Object Detection and Compression in IR Sequences
- 846 Downloads
We consider the problem of remote surveillance using infrared (IR) sensors. The aim is to use IR image sequences to detect moving objects (humans or vehicles), and to transmit a few “best-view images” of every new object that is detected. Since the available bandwidth is usually low, if the object chip is big, it needs to be compressed before being transmitted. Due to low computational power of computing devices attached to the sensor, the algorithms should be computationally simple. We present two approaches for object detection — one which specifically solves the more difficult long-range object detection problem, and the other for objects at short range. For objects at short range, we also present techniques for selecting a single best-view object chip and computationally simple techniques for compressing it to very low bit rates due to the channel bandwidth constraint. A fast image chip compression scheme implemented in the wavelet domain by combining a non-iterative zerotree coding method with 2D-DPCM for both low-and high-frequency subbands is presented. Comparisons with some existing schemes are also included. The object detection and compression algorithms have been implemented in C/C++ and their performance has been evaluated using the Hitachi’s SH4 platform with software simulation.
KeywordsFalse Alarm Object Detection Query Image Compression Scheme Scalar Quantization
Unable to display preview. Download preview PDF.
- Shekarforoush, H., Chellappa, R.: A multi-fractal formalism for stabilization, object detection and tracking in FLIR sequences. In: International Conference on Image Processing. Volume 3. (2000) 78–81Google Scholar
- Elgammal, A., Harwood, D., Davis, L.: Nonparametric background model for background subtraction. In: Proc. 6th European Conf. Computer Vision. Volume 2. (2000) 751–767Google Scholar
- Murase, S., Nayar, S.: Visual learning and recognition of 3-d objects from appearance. International J. Computer Vision 14 (1995) 5–24Google Scholar
- Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cognitive Neuroscience 3 (1991) 71–86Google Scholar
- Turk, M., Pentland, A.: Face recognition using eigenfaces. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition. (1991) 586–591Google Scholar
- Sirovich, L., Kirby, M.: Low dimensional procedures for the characterization of human faces. J. Optical Society of America 4 (1987) 519–524Google Scholar
- Srinivasan, S., Chellappa, R.: Noise-resilient optical flow estimation using overlapped basis functions. J. Optical Society of America 16 (1999) 493–509Google Scholar
- Paek, S., Kim, L.: A real-time wavelet vector quantization algorithm and its vlsi architecture. IEEE Transactions on CSVT 10 (2000) 475–489Google Scholar