On Visual Detection of Highly-occluded Objects for Harvesting Automation in Horticulture

Developing accurate and reliable crop detection algorithms is an important step for harvesting automation in horticulture. This paper presents a novel approach to visual detection of highly-occluded fruits. We use a conditional random field (CRF) on multi-spectral image data (colour and Near-Infrared Reflectance, NIR) to model two classes: crop and background. To describe these two classes, we explore a range of visual-texture features including local binary pattern, histogram of oriented gradients, and learn auto-encoder features. The pro-posed methods are evaluated using hand-labelled images from a dataset captured on a commercial capsicum farm. Experimental results are presented, and performance is evaluated in terms of the Area Under the Curve (AUC) of the precision-recall curves.Our current results achieve a maximum performance of 0.81AUC when combining all of the texture features in conjunction with colour information.

Visual detection of occluded crop: For automated harvesting

This paper presents a novel crop detection system applied to the challenging task of field sweet pepper (capsicum) detection. The field-grown sweet pepper crop presents several challenges for robotic systems such as the high degree of occlusion and the fact that the crop can have a similar colour to the background (green on green). To overcome these issues, we propose a two-stage system that performs per-pixel segmentation followed by region detection. The output of the segmentation is used to search for highly probable regions and declares these to be sweet pepper. We propose the novel use of the local binary pattern (LBP) to perform crop segmentation. This feature improves the accuracy of crop segmentation from an AUC of 0.10, for previously proposed features, to 0.56. Using the LBP feature as the basis for our two-stage algorithm, we are able to detect 69.2% of field grown sweet peppers in three sites. This is an impressive result given that the average detection accuracy of people viewing the same colour imagery is 66.8%.

User-driven saliency maps for evaluating Region-of-Interest detection

Detection of Region of Interest (ROI) in a video leads to more efficient utilization of bandwidth. This is because any ROIs in a given frame can be encoded in higher quality than the rest of that frame, with little or no degradation of quality from the perception of the viewers. Consequently, it is not necessary to uniformly encode the whole video in high quality. One approach to determine ROIs is to use saliency detectors to locate salient regions. This paper proposes a methodology for obtaining ground truth saliency maps to measure the effectiveness of ROI detection by considering the role of user experience during the labelling process of such maps. User perceptions can be captured and incorporated into the definition of salience in a particular video, taking advantage of human visual recall within a given context. Experiments with two state-of-the-art saliency detectors validate the effectiveness of this approach to validating visual saliency in video. This paper will provide the relevant datasets associated with the experiments.

Privacy invasive geo-mashups : privacy 2.0 and the limits of first generation information privacy laws

Online technological advances are pioneering the wider distribution of geospatial information for general mapping purposes. The use of popular web-based applications, such as Google Maps, is ensuring that mapping based applications are becoming commonplace amongst Internet users which has facilitated the rapid growth of geo-mashups. These user generated creations enable Internet users to aggregate and publish information over specific geographical points. This article identifies privacy invasive geo-mashups that involve the unauthorized use of personal information, the inadvertent disclosure of personal information and invasion of privacy issues. Building on Zittrain’s Privacy 2.0, the author contends that first generation information privacy laws, founded on the notions of fair information practices or information privacy principles, may have a limited impact regarding the resolution of privacy problems arising from privacy invasive geo-mashups. Principally because geo-mashups have different patterns of personal information provision, collection, storage and use that reflect fundamental changes in the Web 2.0 environment. The author concludes by recommending embedded technical and social solutions to minimize the risks arising from privacy invasive geo-mashups that could lead to the establishment of guidelines for the general protection of privacy in geo-mashups.

Young children’s experience of visual displays of their artwork

The practice of displaying children's artwork in early childhood classrooms poses a number of questions about the child and his or her visual artwork. This paper focuses on young children’s experiences with the display of their own visual artwork. Following Giorgi's (1985a; 1985b) approach to conducting phenomenological psychological research, 13 children between the ages of 4 and 6 years attending an independent school outside metropolitan Detroit, Michigan (USA) participated in semi-structured interviews as a way of uncovering their lived experiences of seeing their artwork displayed. The study yielded 12 essential themes and from these three key issues and their implications for early childhood art education are explored.

An exploration of varieties of visual attention : ERP findings

A set of five tasks was designed to examine dynamic aspects of visual attention: selective attention to color, selective attention to pattern, dividing and switching attention between color and pattern, and selective attention to pattern with changing target. These varieties of visual attention were examined using the same set of stimuli under different instruction sets; thus differences between tasks cannot be attributed to differences in the perceptual features of the stimuli. ERP data are presented for each of these tasks. A within-task analysis of different stimulus types varying in similarity to the attended target feature revealed that an early frontal selection positivity (FSP) was evident in selective attention tasks, regardless of whether color was the attended feature. The scalp distribution of a later posterior selection negativity (SN) was affected by whether the attended feature was color or pattern. The SN was largely unaffected by dividing attention across color and pattern. A large widespread positivity was evident in most conditions, consisting of at least three subcomponents which were differentially affected by the attention conditions. These findings are discussed in relation to prior research and the time course of visual attention processes in the brain.

Limits of spherical blur determined with an adaptive optics mirror

We extended an earlier study (Vision Research, 45, 1967–1974, 2005) in which we investigated limits at which induced blur of letter targets becomes noticeable, troublesome and objectionable. Here we used a deformable adaptive optics mirror to vary spherical defocus for conditions of a white background with correction of astigmatism; a white background with reduction of all aberrations other than defocus; and a monochromatic background with reduction of all aberrations other than defocus. We used seven cyclopleged subjects, lines of three high-contrast letters as targets, 3–6 mm artificial pupils, and 0.1–0.6 logMAR letter sizes. Subjects used a method of adjustment to control the defocus component of the mirror to set the 'just noticeable', 'just troublesome' and 'just objectionable' defocus levels. For the white-no adaptive optics condition combined with 0.1 logMAR letter size, mean 'noticeable' blur limits were ±0.30, ±0.24 and ±0.23 D at 3, 4 and 6 mm pupils, respectively. White-adaptive optics and monochromatic-adaptive optics conditions reduced blur limits by 8% and 20%, respectively. Increasing pupil size from 3–6 mm decreased blur limits by 29%, and increasing letter size increased blur limits by 79%. Ratios of troublesome to noticeable, and of objectionable to noticeable, blur limits were 1.9 and 2.7 times, respectively. The study shows that the deformable mirror can be used to vary defocus in vision experiments. Overall, the results of noticeable, troublesome and objectionable blur agreed well with those of the previous study. Attempting to reduce higher-order aberrations or chromatic aberrations, reduced blur limits to only a small extent.

The use of high dynamic range luminance mapping in the assessment, understanding and defining of visual issues in post occupancy building assessment

The international focus on embracing daylighting for energy efficient lighting purposes and the corporate sector’s indulgence in the perception of workplace and work practice “transparency” has spurned an increase in highly glazed commercial buildings. This in turn has renewed issues of visual comfort and daylight-derived glare for occupants. In order to ascertain evidence, or predict risk, of these events; appraisals of these complex visual environments require detailed information on the luminances present in an occupant’s field of view. Conventional luminance meters are an expensive and time consuming method of achieving these results. To create a luminance map of an occupant’s visual field using such a meter requires too many individual measurements to be a practical measurement technique. The application of digital cameras as luminance measurement devices has solved this problem. With high dynamic range imaging, a single digital image can be created to provide luminances on a pixel-by-pixel level within the broad field of view afforded by a fish-eye lens: virtually replicating an occupant’s visual field and providing rapid yet detailed luminance information for the entire scene. With proper calibration, relatively inexpensive digital cameras can be successfully applied to the task of luminance measurements, placing them in the realm of tools that any lighting professional should own. This paper discusses how a digital camera can become a luminance measurement device and then presents an analysis of results obtained from post occupancy measurements from building assessments conducted by the Mobile Architecture Built Environment Laboratory (MABEL) project. This discussion leads to the important realisation that the placement of such tools in the hands of lighting professionals internationally will provide new opportunities for the lighting community in terms of research on critical issues in lighting such as daylight glare and visual quality and comfort.

Improved simultaneous computation of motion detection and optical flow for object tracking

Object tracking systems require accurate segmentation of the objects from the background for effective tracking. Motion segmentation or optical flow can be used to segment incoming images. Whilst optical flow allows multiple moving targets to be separated based on their individual velocities, optical flow techniques are prone to errors caused by changing lighting and occlusions, both common in a surveillance environment. Motion segmentation techniques are more robust to fluctuating lighting and occlusions, but don't provide information on the direction of the motion. In this paper we propose a combined motion segmentation/optical flow algorithm for use in object tracking. The proposed algorithm uses the motion segmentation results to inform the optical flow calculations and ensure that optical flow is only calculated in regions of motion, and improve the performance of the optical flow around the edge of moving objects. Optical flow is calculated at pixel resolution and tracking of flow vectors is employed to improve performance and detect discontinuities, which can indicate the location of overlaps between objects. The algorithm is evaluated by attempting to extract a moving target within the flow images, given expected horizontal and vertical movement (i.e. the algorithms intended use for object tracking). Results show that the proposed algorithm outperforms other widely used optical flow techniques for this surveillance application.

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

The use of visual analogue scales to assess motivation to eat in human subjects: a review of their reliability and validity with an evaluation of new hand-held computerized stsytems for temporal tracking of appetite ratings.

This present paper reviews the reliability and validity of visual analogue scales (VAS) in terms of (1) their ability to predict feeding behaviour, (2) their sensitivity to experimental manipulations, and (3) their reproducibility. VAS correlate with, but do not reliably predict, energy intake to the extent that they could be used as a proxy of energy intake. They do predict meal initiation in subjects eating their normal diets in their normal environment. Under laboratory conditions, subjectively rated motivation to eat using VAS is sensitive to experimental manipulations and has been found to be reproducible in relation to those experimental regimens. Other work has found them not to be reproducible in relation to repeated protocols. On balance, it would appear, in as much as it is possible to quantify, that VAS exhibit a good degree of within-subject reliability and validity in that they predict with reasonable certainty, meal initiation and amount eaten, and are sensitive to experimental manipulations. This reliability and validity appears more pronounced under the controlled (but more arti®cial) conditions of the laboratory where the signal : noise ratio in experiments appears to be elevated relative to real life. It appears that VAS are best used in within-subject, repeated-measures designs where the effect of different treatments can be compared under similar circumstances. They are best used in conjunction with other measures (e.g. feeding behaviour, changes in plasma metabolites) rather than as proxies for these variables. New hand-held electronic appetite rating systems (EARS) have been developed to increase reliability of data capture and decrease investigator workload. Recent studies have compared these with traditional pen and paper (P&P) VAS. The EARS have been found to be sensitive to experimental manipulations and reproducible relative to P&P. However, subjects appear to exhibit a signi®cantly more constrained use of the scale when using the EARS relative to the P&P. For this reason it is recommended that the two techniques are not used interchangeably