Complete-linkage clustering for voice activity detection in audio and visual speech

We propose a novel technique for conducting robust voice activity detection (VAD) in high-noise recordings. We use Gaussian mixture modeling (GMM) to train two generic models; speech and non-speech. We then score smaller segments of a given (unseen) recording against each of these GMMs to obtain two respective likelihood scores for each segment. These scores are used to compute a dissimilarity measure between pairs of segments and to carry out complete-linkage clustering of the segments into speech and non-speech clusters. We compare the accuracy of our method against state-of-the-art and standardised VAD techniques to demonstrate an absolute improvement of 15% in half-total error rate (HTER) over the best performing baseline system and across the QUT-NOISE-TIMIT database. We then apply our approach to the Audio-Visual Database of American English (AVDBAE) to demonstrate the performance of our algorithm in using visual, audio-visual or a proposed fusion of these features.

Incorporating visual information for spoken term detection

Spoken term detection (STD) is the task of looking up a spoken term in a large volume of speech segments. In order to provide fast search, speech segments are first indexed into an intermediate representation using speech recognition engines which provide multiple hypotheses for each speech segment. Approximate matching techniques are usually applied at the search stage to compensate the poor performance of automatic speech recognition engines during indexing. Recently, using visual information in addition to audio information has been shown to improve phone recognition performance, particularly in noisy environments. In this paper, we will make use of visual information in the form of lip movements of the speaker in indexing stage and will investigate its effect on STD performance. Particularly, we will investigate if gains in phone recognition accuracy will carry through the approximate matching stage to provide similar gains in the final audio-visual STD system over a traditional audio only approach. We will also investigate the effect of using visual information on STD performance in different noise environments.

The modern primitive and the antipodes: The visual arts and Oceania

In a book seeking to redraw the boundaries between interdisciplinary and transnational modernisms, this chapter contributes to the reorientation in modernist studies by revisiting "primitivism." While no one freely identifies as “primitive,” the spectre of primitivism was a magnet of attraction as well as of critical refusal. It resided on the knife-edge of envy and denunciation, as well as for the projection of alternate imaginative utopias and the worst forms of racial chauvinism. This chapter asserts that primitivism endures as a provocation as much as a utopian aspiration, but it also provides a different understanding of cultures on the "periphery", which is how Antipodean art history has understood itself. The spectre of primitivism not only amplifies the quandaries of modernist cultures—both alerting one to the aesthetic alternatives to modernist cultures, yet also highlighting the fate of traditional culture pitted against modernist cultures, it also suggests the quandaries of a peripheral modernity.

Blur, eye movements and performance on a driving visual recognition slide test

Purpose Optical blur and ageing are known to affect driving performance but their effects on drivers' eye movements are poorly understood. This study examined the effects of optical blur and age on eye movement patterns and performance on the DriveSafe slide recognition test which is purported to predict fitness to drive. Methods Twenty young (27.1 ± 4.6 years) and 20 older (73.3 ± 5.7 years) visually normal drivers performed the DriveSafe under two visual conditions: best-corrected vision and with +2.00 DS blur. The DriveSafe is a Visual Recognition Slide Test that consists of brief presentations of static, real-world driving scenes containing different road users (pedestrians, bicycles and vehicles). Participants reported the types, relative positions and direction of travel of the road users in each image; the score was the number of correctly reported items (maximum score of 128). Eye movements were recorded while participants performed the DriveSafe test using a Tobii TX300 eye tracking system. Results There was a significant main effect of blur on DriveSafe scores (best-corrected: 114.9 vs blur: 93.2; p < 0.001). There was also a significant age and blur interaction on the DriveSafe scores (p < 0.001) such that the young drivers were more negatively affected by blur than the older drivers (reductions of 22% and 13% respectively; p < 0.001): with best-corrected vision, the young drivers performed better than the older drivers (DriveSafe scores: 118.4 vs 111.5; p = 0.001), while with blur, the young drivers performed worse than the older drivers (88.6 vs 95.9; p = 0.009). For the eye movement patterns, blur significantly reduced the number of fixations on road users (best-corrected: 5.1 vs blur: 4.5; p < 0.001), fixation duration on road users (2.0 s vs 1.8 s; p < 0.001) and saccade amplitudes (7.4° vs 6.7°; p < 0.001). A main effect of age on eye movements was also found where older drivers made smaller saccades than the young drivers (6.7° vs 7.4°; p < 0.001). Conclusions Blur reduced DriveSafe scores for both age groups and this effect was greater for the young drivers. The decrease in number of fixations and fixation duration on road users, as well as the reduction in saccade amplitudes under the blurred condition, highlight the difficulty experienced in performing the task in the presence of optical blur, which suggests that uncorrected refractive errors may have a detrimental impact on aspects of driving performance.

Repeatable Condition-Invariant Visual Odometry for Sequence-Based Place Recognition

This paper describes a vision-only system for place recognition in environments that are tra- versed at different times of day, when chang- ing conditions drastically affect visual appear- ance, and at different speeds, where places aren’t visited at a consistent linear rate. The ma- jor contribution is the removal of wheel-based odometry from the previously presented algo- rithm (SMART), allowing the technique to op- erate on any camera-based device; in our case a mobile phone. While we show that the di- rect application of visual odometry to our night- time datasets does not achieve a level of perfor- mance typically needed, the VO requirements of SMART are orthogonal to typical usage: firstly only the magnitude of the velocity is required, and secondly the calculated velocity signal only needs to be repeatable in any one part of the environment over day and night cycles, but not necessarily globally consistent. Our results show that the smoothing effect of motion constraints is highly beneficial for achieving a locally consis- tent, lighting-independent velocity estimate. We also show that the advantage of our patch-based technique used previously for frame recogni- tion, surprisingly, does not transfer to VO, where SIFT demonstrates equally good performance. Nevertheless, we present the SMART system us- ing only vision, which performs sequence-base place recognition in extreme low-light condi- tions where standard 6-DOF VO fails and that improves place recognition performance over odometry-less benchmarks, approaching that of wheel odometry.

Open source computer-vision based guidance system for UAVs on-board decision making

The use of UAVs for remote sensing tasks; e.g. agriculture, search and rescue is increasing. The ability for UAVs to autonomously find a target and perform on-board decision making, such as descending to a new altitude or landing next to a target is a desired capability. Computer-vision functionality allows the Unmanned Aerial Vehicle (UAV) to follow a designated flight plan, detect an object of interest, and change its planned path. In this paper we describe a low cost and an open source system where all image processing is achieved on-board the UAV using a Raspberry Pi 2 microprocessor interfaced with a camera. The Raspberry Pi and the autopilot are physically connected through serial and communicate via MAVProxy. The Raspberry Pi continuously monitors the flight path in real time through USB camera module. The algorithm checks whether the target is captured or not. If the target is detected, the position of the object in frame is represented in Cartesian coordinates and converted into estimate GPS coordinates. In parallel, the autopilot receives the target location approximate GPS and makes a decision to guide the UAV to a new location. This system also has potential uses in the field of Precision Agriculture, plant pest detection and disease outbreaks which cause detrimental financial damage to crop yields if not detected early on. Results show the algorithm is accurate to detect 99% of object of interest and the UAV is capable of navigation and doing on-board decision making.

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%.