Capturing natural-colour 3D models of insects for species discovery and diagnostics

Collections of biological specimens are fundamental to scientific understanding and characterization of natural diversity - past, present and future. This paper presents a system for liberating useful information from physical collections by bringing specimens into the digital domain so they can be more readily shared, analyzed, annotated and compared. It focuses on insects and is strongly motivated by the desire to accelerate and augment current practices in insect taxonomy which predominantly use text, 2D diagrams and images to describe and characterize species. While these traditional kinds of descriptions are informative and useful, they cannot cover insect specimens "from all angles" and precious specimens are still exchanged between researchers and collections for this reason. Furthermore, insects can be complex in structure and pose many challenges to computer vision systems. We present a new prototype for a practical, cost-effective system of off-the-shelf components to acquire natural-colour 3D models of insects from around 3 mm to 30 mm in length. ("Natural-colour" is used to contrast with "false-colour", i.e., colour generated from, or applied to, gray-scale data post-acquisition.) Colour images are captured from different angles and focal depths using a digital single lens reflex (DSLR) camera rig and two-axis turntable. These 2D images are processed into 3D reconstructions using software based on a visual hull algorithm. The resulting models are compact (around 10 megabytes), afford excellent optical resolution, and can be readily embedded into documents and web pages, as well as viewed on mobile devices. The system is portable, safe, relatively affordable, and complements the sort of volumetric data that can be acquired by computed tomography. This system provides a new way to augment the description and documentation of insect species holotypes, reducing the need to handle or ship specimens. It opens up new opportunities to collect data for research, education, art, entertainment, biodiversity assessment and biosecurity control. © 2014 Nguyen et al.

Long-range stereo visual odometry for unmanned aerial vehicles

This thesis explored the utility of long-range stereo visual odometry for application on Unmanned Aerial Vehicles. Novel parameterisations and initialisation routines were developed for the long-range case of stereo visual odometry and new optimisation techniques were implemented to improve the robustness of visual odometry in this difficult scenario. In doing so, the applications of stereo visual odometry were expanded and shown to perform adequately in situations that were previously unworkable.

Detecting rare events using Kullback-Leibler divergence

One main challenge in developing a system for visual surveillance event detection is the annotation of target events in the training data. By making use of the assumption that events with security interest are often rare compared to regular behaviours, this paper presents a novel approach by using Kullback-Leibler (KL) divergence for rare event detection in a weakly supervised learning setting, where only clip-level annotation is available. It will be shown that this approach outperforms state-of-the-art methods on a popular real-world dataset, while preserving real time performance.

Simultaneous underwater visibility assessment, enhancement and improved stereo

Vision-based underwater navigation and obstacle avoidance demands robust computer vision algorithms, particularly for operation in turbid water with reduced visibility. This paper describes a novel method for the simultaneous underwater image quality assessment, visibility enhancement and disparity computation to increase stereo range resolution under dynamic, natural lighting and turbid conditions. The technique estimates the visibility properties from a sparse 3D map of the original degraded image using a physical underwater light attenuation model. Firstly, an iterated distance-adaptive image contrast enhancement enables a dense disparity computation and visibility estimation. Secondly, using a light attenuation model for ocean water, a color corrected stereo underwater image is obtained along with a visibility distance estimate. Experimental results in shallow, naturally lit, high-turbidity coastal environments show the proposed technique improves range estimation over the original images as well as image quality and color for habitat classification. Furthermore, the recursiveness and robustness of the technique allows implementation onboard an Autonomous Underwater Vehicle for improving navigation and obstacle avoidance performance.

Representing team behaviours from noisy data using player role

Due to their unobtrusive nature, vision-based approaches to tracking sports players have been preferred over wearable sensors as they do not require the players to be instrumented for each match. Unfortunately however, due to the heavy occlusion between players, variation in resolution and pose, in addition to fluctuating illumination conditions, tracking players continuously is still an unsolved vision problem. For tasks like clustering and retrieval, having noisy data (i.e. missing and false player detections) is problematic as it generates discontinuities in the input data stream. One method of circumventing this issue is to use an occupancy map, where the field is discretised into a series of zones and a count of player detections in each zone is obtained. A series of frames can then be concatenated to represent a set-play or example of team behaviour. A problem with this approach though is that the compressibility is low (i.e. the variability in the feature space is incredibly high). In this paper, we propose the use of a bilinear spatiotemporal basis model using a role representation to clean-up the noisy detections which operates in a low-dimensional space. To evaluate our approach, we used a fully instrumented field-hockey pitch with 8 fixed high-definition (HD) cameras and evaluated our approach on approximately 200,000 frames of data from a state-of-the-art real-time player detector and compare it to manually labeled data.

Corner detection in images under different noise levels

Corner detection has shown its great importance in many computer vision tasks. However, in real-world applications, noise in the image strongly affects the performance of corner detectors. Few corner detectors have been designed to be robust to heavy noise by now, partly because the noise could be reduced by a denoising procedure. In this paper, we present a corner detector that could find discriminative corners in images contaminated by noise of different levels, without any denoising procedure. Candidate corners (i.e., features) are firstly detected by a modified SUSAN approach, and then false corners in noise are rejected based on their local characteristics. Features in flat regions are removed based on their intensity centroid, and features on edge structures are removed using the Harris response. The detector is self-adaptive to noise since the image signal-to-noise ratio (SNR) is automatically estimated to choose an appropriate threshold for refining features. Experimental results show that our detector has better performance at locating discriminative corners in images with strong noise than other widely used corner or keypoint detectors.

Searching for semantic person queries using channel representations

It is not uncommon to hear a person of interest described by their height, build, and clothing (i.e. type and colour). These semantic descriptions are commonly used by people to describe others, as they are quick to relate and easy to understand. However such queries are not easily utilised within intelligent surveillance systems as they are difficult to transform into a representation that can be searched for automatically in large camera networks. In this paper we propose a novel approach that transforms such a semantic query into an avatar that is searchable within a video stream, and demonstrate state-of-the-art performance for locating a subject in video based on a description.

On the use of optical flow for scene change detection and description

We propose the use of optical flow information as a method for detecting and describing changes in the environment, from the perspective of a mobile camera. We analyze the characteristics of the optical flow signal and demonstrate how robust flow vectors can be generated and used for the detection of depth discontinuities and appearance changes at key locations. To successfully achieve this task, a full discussion on camera positioning, distortion compensation, noise filtering, and parameter estimation is presented. We then extract statistical attributes from the flow signal to describe the location of the scene changes. We also employ clustering and dominant shape of vectors to increase the descriptiveness. Once a database of nodes (where a node is a detected scene change) and their corresponding flow features is created, matching can be performed whenever nodes are encountered, such that topological localization can be achieved. We retrieve the most likely node according to the Mahalanobis and Chi-square distances between the current frame and the database. The results illustrate the applicability of the technique for detecting and describing scene changes in diverse lighting conditions, considering indoor and outdoor environments and different robot platforms.

Reactive reaching and grasping on a humanoid: Towards closing the action-perception loop on the iCub

We propose a system incorporating a tight integration between computer vision and robot control modules on a complex, high-DOF humanoid robot. Its functionality is showcased by having our iCub humanoid robot pick-up objects from a table in front of it. An important feature is that the system can avoid obstacles - other objects detected in the visual stream - while reaching for the intended target object. Our integration also allows for non-static environments, i.e. the reaching is adapted on-the-fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. Furthermore we show that this system can be used both in autonomous and tele-operation scenarios.

Robotics for the mining industry

The mining industry is highly suitable for the application of robotics and automation technology since the work is both arduous and dangerous. However, while the industry makes extensive use of mechanisation it has shown a slow uptake of automation. A major cause of this is the complexity of the task, and the limitations of existing automation technology which is predicated on a structured and time invariant working environment. Here we discuss the topic of mining automation from a robotics and computer vision perspective — as a problem in sensor based robot control, an issue which the robotics community has been studying for nearly two decades. We then describe two of our current mining automation projects to demonstrate what is possible for both open-pit and underground mining operations.

Parallel attentive visual tracking

The research reported here addresses the problem of detecting and tracking independently moving objects from a moving observer in real-time, using corners as object tokens. Corners are detected using the Harris corner detector, and local image-plane constraints are employed to solve the correspondence problem. The approach relaxes the restrictive static-world assumption conventionally made, and is therefore capable of tracking independently moving and deformable objects. Tracking is performed without the use of any 3-dimensional motion model. The technique is novel in that, unlike traditional feature-tracking algorithms where feature detection and tracking is carried out over the entire image-plane, here it is restricted to those areas most likely to contain-meaningful image structure. Two distinct types of instantiation regions are identified, these being the “focus-of-expansion” region and “border” regions of the image-plane. The size and location of these regions are defined from a combination of odometry information and a limited knowledge of the operating scenario. The algorithms developed have been tested on real image sequences taken from typical driving scenarios. Implementation of the algorithm using T800 Transputers has shown that near-linear speedups are achievable, and that real-time operation is possible (half-video rate has been achieved using 30 processing elements).

Robust sensing for a 3,500 tonne field robot

The mining industry is highly suitable for the application of robotics and automation technology since the work is arduous, dangerous and often repetitive. This paper discusses a robust sensing system developed to find and trade the position of the hoist ropes of a dragline. Draglines are large `walking cranes' used in open-pit coal mining to remove the material covering the coal seam. The rope sensing system developed uses two time-of-flight laser scanners. The finding algorithm uses a novel data association and tracking strategy based on pairing rope data.

Robot control of a 3,500 tonne mining machine

The mining industry is highly suitable for the application of robotics and automation technology since the work is arduous, dangerous and often repetitive. This paper describes the development of an automation system for a physically large and complex field robotic system - a 3,500 tonne mining machine (a dragline). The major components of the system are discussed with a particular emphasis on the machine/operator interface. A very important aspect of this system is that it must work cooperatively with a human operator, seamlessly passing the control back and forth in order to achieve the main aim - increased productivity.