Computer vision tools for low-cost and noninvasive measurement of autism-related behaviors in infants.

The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated which promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests that behavioral signs can be observed late in the first year of life. Many of these studies involve extensive frame-by-frame video observation and analysis of a child's natural behavior. Although nonintrusive, these methods are extremely time-intensive and require a high level of observer training; thus, they are burdensome for clinical and large population research purposes. This work is a first milestone in a long-term project on non-invasive early observation of children in order to aid in risk detection and research of neurodevelopmental disorders. We focus on providing low-cost computer vision tools to measure and identify ASD behavioral signs based on components of the Autism Observation Scale for Infants (AOSI). In particular, we develop algorithms to measure responses to general ASD risk assessment tasks and activities outlined by the AOSI which assess visual attention by tracking facial features. We show results, including comparisons with expert and nonexpert clinicians, which demonstrate that the proposed computer vision tools can capture critical behavioral observations and potentially augment the clinician's behavioral observations obtained from real in-clinic assessments.

Object segregation and local gist vision using low-level geometry

Multi-scale representations of lines, edges and keypoints on the basis of simple, complex and end-stopped cells can be used for object categorisation and recognition (Rodrigues and du Buf, 2009 BioSystems 95 206-226). These representations are complemented by saliency maps of colour, texture, disparity and motion information, which also serve to model extremely fast gist vision in parallel with object segregation. We present a low-level geometry model based on a single type of self-adjusting grouping cell, with a circular array of dendrites connected to edge cells located at several angles.

A Survey on FPGA-Based Sensor Systems: Towards Intelligent and Reconfigurable Low-Power Sensors for Computer Vision, Control and Signal Processing

The current trend in the evolution of sensor systems seeks ways to provide more accuracy and resolution, while at the same time decreasing the size and power consumption. The use of Field Programmable Gate Arrays (FPGAs) provides specific reprogrammable hardware technology that can be properly exploited to obtain a reconfigurable sensor system. This adaptation capability enables the implementation of complex applications using the partial reconfigurability at a very low-power consumption. For highly demanding tasks FPGAs have been favored due to the high efficiency provided by their architectural flexibility (parallelism, on-chip memory, etc.), reconfigurability and superb performance in the development of algorithms. FPGAs have improved the performance of sensor systems and have triggered a clear increase in their use in new fields of application. A new generation of smarter, reconfigurable and lower power consumption sensors is being developed in Spain based on FPGAs. In this paper, a review of these developments is presented, describing as well the FPGA technologies employed by the different research groups and providing an overview of future research within this field.

Batting with occluded vision: An in situ examination of the information pick-up and interceptive skills of high- and low-skilled cricket batsmen

The capability of cricket batsmen of different skill levels to pick-up information from the pre-release movement pattern of the bowler, from pre-bounce ball flight, and from post-bounce ball flight was examined experimentally. Six highly skilled and six low-skilled cricket batsmen batted against three different leg-spin bowlers while wearing liquid crystal spectacles. The spectacles permitted the specific information available to the batsmen on each trial to be manipulated such that vision was either: (i) occluded at a point prior to the point of ball release (thereby only allowing vision of advance information from the bowler's delivery action); (ii) occluded at a point prior to the point of bat[ bounce (thereby permitting the additional vision of pre-bounce ball flight); or (iii) not occluded (thereby permitting the additional vision of post-bounce bat[ flight information). Measurement was made on each trial of both the accuracy of the definitive (forward-backward) foot movements made by the batsmen and their success (or otherwise) in making bat-bat[ contact. The analyses revealed a superior capability of the more skilled players to make use of earlier (pre-bounce) bat[ flight information to guide successful bat-bat[ interception, thus mirroring the greater use of prospective information pick-up by skilled performers observed in other aspects of batting and in other time-constrained performance domains. (c) 2006 Sports Medicine Australia. Published by Elsevier Ltd. All rights reserved.

Local edge detectors: A substrate for fine spatial vision at low temporal frequencies in rabbit retina

Visual acuity is limited by the size and density of the smallest retinal ganglion cells, which correspond to the midget ganglion cells in primate retina and the beta- ganglion cells in cat retina, both of which have concentric receptive fields that respond at either light- On or light- Off. In contrast, the smallest ganglion cells in the rabbit retina are the local edge detectors ( LEDs), which respond to spot illumination at both light- On and light- Off. However, the LEDs do not predominate in the rabbit retina and the question arises, what role do they play in fine spatial vision? We studied the morphology and physiology of LEDs in the isolated rabbit retina and examined how their response properties are shaped by the excitatory and inhibitory inputs. Although the LEDs comprise only similar to 15% of the ganglion cells, neighboring LEDs are separated by 30 - 40 mu m on the visual streak, which is sufficient to account for the grating acuity of the rabbit. The spatial and temporal receptive- field properties of LEDs are generated by distinct inhibitory mechanisms. The strong inhibitory surround acts presynaptically to suppress both the excitation and the inhibition elicited by center stimulation. The temporal properties, characterized by sluggish onset, sustained firing, and low bandwidth, are mediated by the temporal properties of the bipolar cells and by postsynaptic interactions between the excitatory and inhibitory inputs. We propose that the LEDs signal fine spatial detail during visual fixation, when high temporal frequencies are minimal.

Low level feature detection in human vision

Influential models of edge detection have generally supposed that an edge is detected at peaks in the 1st derivative of the luminance profile, or at zero-crossings in the 2nd derivative. However, when presented with blurred triangle-wave images, observers consistently marked edges not at these locations, but at peaks in the 3rd derivative. This new phenomenon, termed ‘Mach edges’ persisted when a luminance ramp was added to the blurred triangle-wave. Modelling of these Mach edge detection data required the addition of a physiologically plausible filter, prior to the 3rd derivative computation. A viable alternative model was examined, on the basis of data obtained with short-duration, high spatial-frequency stimuli. Detection and feature-making methods were used to examine the perception of Mach bands in an image set that spanned a range of Mach band detectabilities. A scale-space model that computed edge and bar features in parallel provided a better fit to the data than 4 competing models that combined information across scale in a different manner, or computed edge or bar features at a single scale. The perception of luminance bars was examined in 2 experiments. Data for one image-set suggested a simple rule for perception of a small Gaussian bar on a larger inverted Gaussian bar background. In previous research, discriminability (d’) has typically been reported to be a power function of contrast, where the exponent (p) is 2 to 3. However, using bar, grating, and Gaussian edge stimuli, with several methodologies, values of p were obtained that ranged from 1 to 1.7 across 6 experiments. This novel finding was explained by appealing to low stimulus uncertainty, or a near-linear transducer.

Contrast sensitivity changes due to glaucoma and normal aging: low-spatial-frequency losses in both magnocellular and parvocellular pathways

PURPOSE: To explore the effects of glaucoma and aging on low-spatial-frequency contrast sensitivity by using tests designed to assess performance of either the magnocellular (M) or parvocellular (P) visual pathways. METHODS: Contrast sensitivity was measured for spatial frequencies of 0.25 to 2 cyc/deg by using a published steady- and pulsed-pedestal approach. Sixteen patients with glaucoma and 16 approximately age-matched control subjects participated. Patients with glaucoma were tested foveally and at two midperipheral locations: (1) an area of early visual field loss, and (2) an area of normal visual field. Control subjects were assessed in matched locations. An additional group of 12 younger control subjects (aged 20-35 years) were also tested. RESULTS: Older control subjects demonstrated reduced sensitivity relative to the younger group for the steady (presumed M)- and pulsed (presumed P)-pedestal conditions. Sensitivity was reduced foveally and in the midperiphery across the spatial frequency range. In the area of early visual field loss, the glaucoma group demonstrated further sensitivity reduction relative to older control subjects across the spatial frequency range for both the steady- and pulsed-pedestal tasks. Sensitivity was also reduced in the midperipheral location of "normal" visual field for the pulsed condition. CONCLUSIONS: Normal aging results in a reduction of contrast sensitivity for the low-spatial-frequency-sensitive components of both the M and P pathways. Glaucoma results in a further reduction of sensitivity that is not selective for M or P function. The low-spatial-frequency-sensitive channels of both pathways, which are presumably mediated by cells with larger receptive fields, are approximately equivalently impaired in early glaucoma.

A Vision Based Target Detection System for Docking of an Autonomous Underwater Vehicle

This paper describes the development and preliminary experimental evaluation of a visionbased docking system to allow an Autonomous Underwater Vehicle (AUV) to identify and attach itself to a set of uniquely identifiable targets. These targets, docking poles, are detected using Haar rectangular features and rotation of integral images. A non-holonomic controller allows the Starbug AUV to orient itself with respect to the target whilst maintaining visual contact during the manoeuvre. Experimental results show the proposed vision system is capable of robustly identifying a pair of docking poles simultaneously in a variety of orientations and lighting conditions. Experiments in an outdoor pool show that this vision system enables the AUV to dock autonomously from a distance of up to 4m with relatively low visibility.

Image synthesis based on a model of human vision

Modern computer graphics systems are able to construct renderings of such high quality that viewers are deceived into regarding the images as coming from a photographic source. Large amounts of computing resources are expended in this rendering process, using complex mathematical models of lighting and shading. However, psychophysical experiments have revealed that viewers only regard certain informative regions within a presented image. Furthermore, it has been shown that these visually important regions contain low-level visual feature differences that attract the attention of the viewer. This thesis will present a new approach to image synthesis that exploits these experimental findings by modulating the spatial quality of image regions by their visual importance. Efficiency gains are therefore reaped, without sacrificing much of the perceived quality of the image. Two tasks must be undertaken to achieve this goal. Firstly, the design of an appropriate region-based model of visual importance, and secondly, the modification of progressive rendering techniques to effect an importance-based rendering approach. A rule-based fuzzy logic model is presented that computes, using spatial feature differences, the relative visual importance of regions in an image. This model improves upon previous work by incorporating threshold effects induced by global feature difference distributions and by using texture concentration measures. A modified approach to progressive ray-tracing is also presented. This new approach uses the visual importance model to guide the progressive refinement of an image. In addition, this concept of visual importance has been incorporated into supersampling, texture mapping and computer animation techniques. Experimental results are presented, illustrating the efficiency gains reaped from using this method of progressive rendering. This visual importance-based rendering approach is expected to have applications in the entertainment industry, where image fidelity may be sacrificed for efficiency purposes, as long as the overall visual impression of the scene is maintained. Different aspects of the approach should find many other applications in image compression, image retrieval, progressive data transmission and active robotic vision.

Vision-based detection and tracking of aerial targets for UAV collision avoidance

Machine vision represents a particularly attractive solution for sensing and detecting potential collision-course targets due to the relatively low cost, size, weight, and power requirements of the sensors involved (as opposed to radar). This paper describes the development and evaluation of a vision-based collision detection algorithm suitable for fixed-wing aerial robotics. The system was evaluated using highly realistic vision data of the moments leading up to a collision. Based on the collected data, our detection approaches were able to detect targets at distances ranging from 400m to about 900m. These distances (with some assumptions about closing speeds and aircraft trajectories) translate to an advanced warning of between 8-10 seconds ahead of impact, which approaches the 12.5 second response time recommended for human pilots. We make use of the enormous potential of graphic processing units to achieve processing rates of 30Hz (for images of size 1024-by- 768). Currently, integration in the final platform is under way.

Airborne vision-based collision-detection system

Machine vision represents a particularly attractive solution for sensing and detecting potential collision-course targets due to the relatively low cost, size, weight, and power requirements of vision sensors (as opposed to radar and TCAS). This paper describes the development and evaluation of a real-time vision-based collision detection system suitable for fixed-wing aerial robotics. Using two fixed-wing UAVs to recreate various collision-course scenarios, we were able to capture highly realistic vision (from an onboard camera perspective) of the moments leading up to a collision. This type of image data is extremely scarce and was invaluable in evaluating the detection performance of two candidate target detection approaches. Based on the collected data, our detection approaches were able to detect targets at distances ranging from 400m to about 900m. These distances (with some assumptions about closing speeds and aircraft trajectories) translate to an advanced warning of between 8-10 seconds ahead of impact, which approaches the 12.5 second response time recommended for human pilots. We overcame the challenge of achieving real-time computational speeds by exploiting the parallel processing architectures of graphics processing units found on commercially-off-the-shelf graphics devices. Our chosen GPU device suitable for integration onto UAV platforms can be expected to handle real-time processing of 1024 by 768 pixel image frames at a rate of approximately 30Hz. Flight trials using manned Cessna aircraft where all processing is performed onboard will be conducted in the near future, followed by further experiments with fully autonomous UAV platforms.

Helicopter automation using a low-cost sensing system

This paper details the design of an autonomous helicopter control system using a low cost sensor suite. Control is maintained using simple nested PID loops. Aircraft attitude, velocity, and height is estimated using an in-house designed IMU and vision system. Information is combined using complimentary filtering. The aircraft is shown to be stabilised and responding to high level demands on all axes, including heading, height, lateral velocity and longitudinal velocity.

Helicopter automation using a low-cost sensing system

This paper details the design of an autonomous helicopter control system using a low cost sensor suite. Control is maintained using simple nested PID loops. Aircraft attitude, velocity, and height is estimated using an in-house designed IMU and vision system. Information is combined using complimentary filtering. The aircraft is shown to be stabilised and responding to high level demands on all axes, including heading, height, lateral velocity and longitudinal velocity.