Conference Paper

A Two-Dimensional, Object-Based Analog VLSI Visual Attention System.

Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA
DOI: 10.1109/ARVLSI.1999.756055 Conference: 18th Conference on Advanced Research in VLSI (ARVLSI '99), 21-24 March 1999, Atlanta, GA, USA
Source: DBLP

ABSTRACT A two-dimensional object-based analog VLSI model of selective attentional processing has been implemented using a standard 1.2 μm CMOS process. This chip extends previous work modeling object-based selection and scanning by incorporating the circuity and architectural changes necessary for two-dimensional focal plane processing. To balance the need for closely spaced large photodetectors with the space requirements of complex in-pixel processing, the chip implements a multiresolution architecture. The system has he ability to group pixels into objects; this grouping is dynamic, driven solely by the segmentation criterion at the input. In the demonstration system, image intensity has been chosen for the input saliency map and the segmentation is based on spatial lowpass filtering followed by an intensity threshold. We present experimental results

Download full-text

Full-text

Available from: Stephen P Deweerth, Aug 13, 2015
1 Follower
 · 
60 Views
  • Source
    • "To further increase processing speed the smart vision sensor can be made to select the sub-regions of the image that require processing, preprocess them, and transmit only the data from those subregions . Sensors that carry out this type of operation have been recently proposed [5] [6]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a CMOS VLSI image sensor containing a 26×26 array of differentiating adaptive photoreceptors, combined with a current-mode hysteretic winner-take-all (WTA) network, able to detect and track high-contrast targets moving within its field of view. The device, implemented using standard 0.8 μm CMOS technology, dissipates 600 μW, with a power supply voltage of 5 V. Its WTA outputs can be read out using either analog position-to-voltage circuits, or digital address encoders. Photoreceptor voltages with sustained and transient responses can be read out serially using an on-chip scanner, or in a random-access mode using address decoders. Combining digital output position encoders and input address decoders, it is possible to read only the location of the winning pixel, or a small window around the winning pixel (e.g. using a microcontroller), thus implementing a selective attention read-out mechanism.
    Circuits and Systems, 2002. ISCAS 2002. IEEE International Symposium on; 02/2002
  • Source
    • "Several VLSI systems for implementing visual selective-attention mechanisms have also been presented [14]–[17], [8]. These systems contain photosensing elements and signal–processing elements on the same focal plane, and apply a competitive selection process to visual stimuli sensed and processed by the focal plane processor itself. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Detailed processing of sensory information is a computationally demanding task. This is especially true for vision, where the amount of information provided by the sensors typically exceeds the processing capacity of the system. Rather than attempting to process all the sensory data simultaneously, an effective strategy is to focus on subregions of the input space, shifting from one, subregion to the other, in a serial fashion. This strategy is commonly referred to as selective attention. We present a neuromorphic active-vision system, that implements a saliency-based model of selective attention. Visual data is sensed and preprocessed in parallel by a transient imager chip and transmitted to a selective-attention chip. This chip sequentially selects the spatial locations of salient regions in the vision sensor's field of view. A host computer uses the output of the selective-attention chip to drive the motors on which the imager is mounted, and to orient it toward the selected regions. The system's design framework is modular and allows the integration of multiple sensors and multiple selective-attention chips. We present experimental results showing the performance of a two-chip system in response to well-controlled test stimuli and to natural stimuli
    IEEE Transactions on Circuits and Systems II Analog and Digital Signal Processing 06/2001; 48(5-48):492 - 500. DOI:10.1109/82.938359
Show more