Advantages of Selective Change-Driven Vision for Resource-Limited Systems
ABSTRACT Selective change-driven (SCD) vision is a capture/processing strategy especially suited for vision systems with limited resources and/or vision applications with real-time constraints. SCD vision capture essentially involves delivering only the pixels that have undergone the greatest change in illumination since the last time they were read-out. SCD vision processing involves processing a limited pixel flow with similar results to the usual image flow, but with far lower bandwidth and processing requirements. SCD vision is based on pixel flow processing instead of traditional image flow processing. This complete change in the way video is processed and has a direct impact on the processing hardware required to deal with visual information. In this paper, we present the first CMOS sensor using the SCD strategy, along with a highly resource-limited system implementing an object tracking experiment. Results show that SCD vision outperforms traditional vision systems by at least one order of magnitude, with limited hardware requirements for the specific tracking experiment being tested.
- SourceAvailable from: upenn.edu[show abstract] [hide abstract]
ABSTRACT: Seeking to match the brain's computational efficiency, we draw inspiration from its neural circuits. To model the four main output (ganglion) cell types found in the retina, we morphed outer and inner retina circuits into a 96 x 60-photoreceptor, 3.5 x 3.3 mm2, 0.35 microm-CMOS chip. Our retinomorphic chip produces spike trains for 3600 ganglion cells (GCs), and consumes 62.7 mW at 45 spikes/s/GC. This chip, which is the first silicon retina to successfully model inner retina circuitry, approaches the spatial density of the retina. We present experimental measurements showing that the chip's subthreshold current-mode circuits realize luminance adaptation, bandpass spatiotemporal filtering, temporal adaptation and contrast gain control. The four different GC outputs produced by our chip encode light onset or offset in a sustained or transient fashion, producing a quadrature-like representation. The retinomorphic chip's circuit design is described in a companion paper [Zaghloul and Boahen (2004)].IEEE Transactions on Biomedical Engineering 05/2004; 51(4):667-75. · 2.35 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: A vision sensor for low-cost, fast, and robust vision systems is described. The sensor includes an on-chip analog computation of contrast magnitude and direction of image features. A temporal ordering of this information according to the contrast magnitude is used to reduce the amount of data delivered. This sensor, realized in a 0.5-μm two-poly three-metal technology, features a contrast sensitivity of 2%, a contrast direction precision of ±3°, and an illumination dynamic range of 120 dB. Applications with uncontrolled lighting conditions are ideal for this sensor.IEEE Journal of Solid-State Circuits 01/2004; · 3.06 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: We propose a novel integration of image compression and sensing in order to enhance the performance of an image sensor. By integrating a compression function onto the sensor focal plane, the image signal to be read out from the sensor is significantly reduced and the pixel rate of the sensor ran consequently be increased. The potential applications of the proposed sensor are in high pixel-rate imaging, such as high frame-rate image sensing and high-resolution image sensing. The compression scheme we employ is a conditional replenishment, which detects and encodes moving areas. In this paper, we introduce two architectures for on-sensor compression; one is the pixel parallel approach and the other is the column parallel approach. We prototyped a VLSI chip of the proposed sensor based on the pixel parallel architecture. We show the design and describe the results of the experiments obtained by the prototype chipIEEE Transactions on Electron Devices 11/1997; · 2.06 Impact Factor