Person re-identification using group information

After first observing a person, the task of person re-identification involves recognising an individual at different locations across a network of cameras at a later time. Traditionally, this task has been performed by first extracting appearance features of an individual and then matching these features to the previous observation. However, identifying an individual based solely on appearance can be ambiguous, particularly when people wear similar clothing (i.e. people dressed in uniforms in sporting and school settings). This task is made more difficult when the resolution of the input image is small as is typically the case in multi-camera networks. To circumvent these issues, we need to use other contextual cues. In this paper, we use "group" information as our contextual feature to aid in the re-identification of a person, which is heavily motivated by the fact that people generally move together as a collective group. To encode group context, we learn a linear mapping function to assign each person to a "role" or position within the group structure. We then combine the appearance and group context cues using a weighted summation. We demonstrate how this improves performance of person re-identification in a sports environment over appearance based-features.

Scene invariant multi camera crowd counting

Automated crowd counting has become an active field of computer vision research in recent years. Existing approaches are scene-specific, as they are designed to operate in the single camera viewpoint that was used to train the system. Real world camera networks often span multiple viewpoints within a facility, including many regions of overlap. This paper proposes a novel scene invariant crowd counting algorithm that is designed to operate across multiple cameras. The approach uses camera calibration to normalise features between viewpoints and to compensate for regions of overlap. This compensation is performed by constructing an 'overlap map' which provides a measure of how much an object at one location is visible within other viewpoints. An investigation into the suitability of various feature types and regression models for scene invariant crowd counting is also conducted. The features investigated include object size, shape, edges and keypoints. The regression models evaluated include neural networks, K-nearest neighbours, linear and Gaussian process regresion. Our experiments demonstrate that accurate crowd counting was achieved across seven benchmark datasets, with optimal performance observed when all features were used and when Gaussian process regression was used. The combination of scene invariance and multi camera crowd counting is evaluated by training the system on footage obtained from the QUT camera network and testing it on three cameras from the PETS 2009 database. Highly accurate crowd counting was observed with a mean relative error of less than 10%. Our approach enables a pre-trained system to be deployed on a new environment without any additional training, bringing the field one step closer toward a 'plug and play' system.

Rank minimization across appearance and shape for AAM ensemble fitting

Active Appearance Models (AAMs) employ a paradigm of inverting a synthesis model of how an object can vary in terms of shape and appearance. As a result, the ability of AAMs to register an unseen object image is intrinsically linked to two factors. First, how well the synthesis model can reconstruct the object image. Second, the degrees of freedom in the model. Fewer degrees of freedom yield a higher likelihood of good fitting performance. In this paper we look at how these seemingly contrasting factors can complement one another for the problem of AAM fitting of an ensemble of images stemming from a constrained set (e.g. an ensemble of face images of the same person).

Distributed low-power image processing in wireless sensor networks for intelligent video surveillance applications

Distributed Wireless Smart Camera (DWSC) network is a special type of Wireless Sensor Network (WSN) that processes captured images in a distributed manner. While image processing on DWSCs sees a great potential for growth, with its applications possessing a vast practical application domain such as security surveillance and health care, it suffers from tremendous constraints. In addition to the limitations of conventional WSNs, image processing on DWSCs requires more computational power, bandwidth and energy that presents significant challenges for large scale deployments. This dissertation has developed a number of algorithms that are highly scalable, portable, energy efficient and performance efficient, with considerations of practical constraints imposed by the hardware and the nature of WSN. More specifically, these algorithms tackle the problems of multi-object tracking and localisation in distributed wireless smart camera net- works and optimal camera configuration determination. Addressing the first problem of multi-object tracking and localisation requires solving a large array of sub-problems. The sub-problems that are discussed in this dissertation are calibration of internal parameters, multi-camera calibration for localisation and object handover for tracking. These topics have been covered extensively in computer vision literatures, however new algorithms must be invented to accommodate the various constraints introduced and required by the DWSC platform. A technique has been developed for the automatic calibration of low-cost cameras which are assumed to be restricted in their freedom of movement to either pan or tilt movements. Camera internal parameters, including focal length, principal point, lens distortion parameter and the angle and axis of rotation, can be recovered from a minimum set of two images of the camera, provided that the axis of rotation between the two images goes through the camera's optical centre and is parallel to either the vertical (panning) or horizontal (tilting) axis of the image. For object localisation, a novel approach has been developed for the calibration of a network of non-overlapping DWSCs in terms of their ground plane homographies, which can then be used for localising objects. In the proposed approach, a robot travels through the camera network while updating its position in a global coordinate frame, which it broadcasts to the cameras. The cameras use this, along with the image plane location of the robot, to compute a mapping from their image planes to the global coordinate frame. This is combined with an occupancy map generated by the robot during the mapping process to localised objects moving within the network. In addition, to deal with the problem of object handover between DWSCs of non-overlapping fields of view, a highly-scalable, distributed protocol has been designed. Cameras that follow the proposed protocol transmit object descriptions to a selected set of neighbours that are determined using a predictive forwarding strategy. The received descriptions are then matched at the subsequent camera on the object's path using a probability maximisation process with locally generated descriptions. The second problem of camera placement emerges naturally when these pervasive devices are put into real use. The locations, orientations, lens types etc. of the cameras must be chosen in a way that the utility of the network is maximised (e.g. maximum coverage) while user requirements are met. To deal with this, a statistical formulation of the problem of determining optimal camera configurations has been introduced and a Trans-Dimensional Simulated Annealing (TDSA) algorithm has been proposed to effectively solve the problem.

Experiments with cooperative control of underwater robots

In this paper we describe cooperative control algorithms for robots and sensor nodes in an underwater environment. Cooperative navigation is defined as the ability of a coupled system of autonomous robots to pool their resources to achieve long-distance navigation and a larger controllability space. Other types of useful cooperation in underwater environments include: exchange of information such as data download and retasking; cooperative localization and tracking; and physical connection (docking) for tasks such as deployment of underwater sensor networks, collection of nodes and rescue of damaged robots. We present experimental results obtained with an underwater system that consists of two very different robots and a number of sensor network modules. We present the hardware and software architecture of this underwater system. We then describe various interactions between the robots and sensor nodes and between the two robots, including cooperative navigation. Finally, we describe our experiments with this underwater system and present data.

Real-time video event detection in crowded scenes using MPEG derived features : a multiple instance learning approach

This paper presents an investigation into event detection in crowded scenes, where the event of interest co-occurs with other activities and only binary labels at the clip level are available. The proposed approach incorporates a fast feature descriptor from the MPEG domain, and a novel multiple instance learning (MIL) algorithm using sparse approximation and random sensing. MPEG motion vectors are used to build particle trajectories that represent the motion of objects in uniform video clips, and the MPEG DCT coefficients are used to compute a foreground map to remove background particles. Trajectories are transformed into the Fourier domain, and the Fourier representations are quantized into visual words using the K-Means algorithm. The proposed MIL algorithm models the scene as a linear combination of independent events, where each event is a distribution of visual words. Experimental results show that the proposed approaches achieve promising results for event detection compared to the state-of-the-art.

Nonrigid face alignment for unknown subject in video

Non-rigid face alignment is a very important task in a large range of applications but the existing tracking based non-rigid face alignment methods are either inaccurate or requiring person-specific model. This dissertation has developed simultaneous alignment algorithms that overcome these constraints and provide alignment with high accuracy, efficiency, robustness to varying image condition, and requirement of only generic model.

Towards persistent visual navigation using SMART

In this paper, we present SMART (Sequence Matching Across Route Traversals): a vision- based place recognition system that uses whole image matching techniques and odometry information to improve the precision-recall performance, latency and general applicability of the SeqSLAM algorithm. We evaluate the system’s performance on challenging day and night journeys over several kilometres at widely varying vehicle velocities from 0 to 60 km/h, compare performance to the current state-of- the-art SeqSLAM algorithm, and provide parameter studies that evaluate the effectiveness of each system component. Using 30-metre sequences, SMART achieves place recognition performance of 81% recall at 100% precision, outperforming SeqSLAM, and is robust to significant degradations in odometry.

Enabling aircraft emergency landings using active visual site detection

The ability to automate forced landings in an emergency such as engine failure is an essential ability to improve the safety of Unmanned Aerial Vehicles operating in General Aviation airspace. By using active vision to detect safe landing zones below the aircraft, the reliability and safety of such systems is vastly improved by gathering up-to-the-minute information about the ground environment. This paper presents the Site Detection System, a methodology utilising a downward facing camera to analyse the ground environment in both 2D and 3D, detect safe landing sites and characterise them according to size, shape, slope and nearby obstacles. A methodology is presented showing the fusion of landing site detection from 2D imagery with a coarse Digital Elevation Map and dense 3D reconstructions using INS-aided Structure-from-Motion to improve accuracy. Results are presented from an experimental flight showing the precision/recall of landing sites in comparison to a hand-classified ground truth, and improved performance with the integration of 3D analysis from visual Structure-from-Motion.

An evaluation of different features and learning models for anomalous event detection

The huge amount of CCTV footage available makes it very burdensome to process these videos manually through human operators. This has made automated processing of video footage through computer vision technologies necessary. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned ‘normal’ model. There is no precise and exact definition for an abnormal activity; it is dependent on the context of the scene. Hence there is a requirement for different feature sets to detect different kinds of abnormal activities. In this work we evaluate the performance of different state of the art features to detect the presence of the abnormal objects in the scene. These include optical flow vectors to detect motion related anomalies, textures of optical flow and image textures to detect the presence of abnormal objects. These extracted features in different combinations are modeled using different state of the art models such as Gaussian mixture model(GMM) and Semi- 2D Hidden Markov model(HMM) to analyse the performances. Further we apply perspective normalization to the extracted features to compensate for perspective distortion due to the distance between the camera and objects of consideration. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

A security system based on human iris identification using wavelet transform

A security system based on the recognition of the iris of human eyes using the wavelet transform is presented. The zero-crossings of the wavelet transform are used to extract the unique features obtained from the grey-level profiles of the iris. The recognition process is performed in two stages. The first stage consists of building a one-dimensional representation of the grey-level profiles of the iris, followed by obtaining the wavelet transform zerocrossings of the resulting representation. The second stage is the matching procedure for iris recognition. The proposed approach uses only a few selected intermediate resolution levels for matching, thus making it computationally efficient as well as less sensitive to noise and quantisation errors. A normalisation process is implemented to compensate for size variations due to the possible changes in the camera-to-face distance. The technique has been tested on real images in both noise-free and noisy conditions. The technique is being investigated for real-time implementation, as a stand-alone system, for access control to high-security areas.

Video analytics for the detection of near-miss incidents on approach to railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand causal factors that contribute to these accidents, the Cooperative Research Centre for Rail Innovation is running a project entitled Baseline Level Crossing Video. The project aims to improve the recording of level crossing safety data by developing an intelligent system capable of detecting near-miss incidents and capturing quantitative data around these incidents. To detect near-miss events at railway level crossings a video analytics module is being developed to analyse video footage obtained from forward-facing cameras installed on trains. This paper presents a vision base approach for the detection of these near-miss events. The video analytics module is comprised of object detectors and a rail detection algorithm, allowing the distance between a detected object and the rail to be determined. An existing publicly available Histograms of Oriented Gradients (HOG) based object detector algorithm is used to detect various types of vehicles in each video frame. As vehicles are usually seen from a sideway view from the cabin’s perspective, the results of the vehicle detector are verified using an algorithm that can detect the wheels of each detected vehicle. Rail detection is facilitated using a projective transformation of the video, such that the forward-facing view becomes a bird’s eye view. Line Segment Detector is employed as the feature extractor and a sliding window approach is developed to track a pair of rails. Localisation of the vehicles is done by projecting the results of the vehicle and rail detectors on the ground plane allowing the distance between the vehicle and rail to be calculated. The resultant vehicle positions and distance are logged to a database for further analysis. We present preliminary results regarding the performance of a prototype video analytics module on a data set of videos containing more than 30 different railway level crossings. The video data is captured from a journey of a train that has passed through these level crossings.

Mawson the astrobiologist rover : towards automatic recognition of stromatolites

This work aims at developing a planetary rover capable of acting as an assistant astrobiologist: making a preliminary analysis of the collected visual images that will help to make better use of the scientists time by pointing out the most interesting pieces of data. This paper focuses on the problem of detecting and recognising particular types of stromatolites. Inspired by the processes actual astrobiologists go through in the field when identifying stromatolites, the processes we investigate focus on recognising characteristics associated with biogenicity. The extraction of these characteristics is based on the analysis of geometrical structure enhanced by passing the images of stromatolites into an edge-detection filter and its Fourier Transform, revealing typical spatial frequency patterns. The proposed analysis is performed on both simulated images of stromatolite structures and images of real stromatolites taken in the field by astrobiologists.

Reliable automatic camera-laser calibration

Camera-laser calibration is necessary for many robotics and computer vision applications. However, existing calibration toolboxes still require laborious effort from the operator in order to achieve reliable and accurate results. This paper proposes algorithms that augment two existing trustful calibration methods with an automatic extraction of the calibration object from the sensor data. The result is a complete procedure that allows for automatic camera-laser calibration. The first stage of the procedure is automatic camera calibration which is useful in its own right for many applications. The chessboard extraction algorithm it provides is shown to outperform openly available techniques. The second stage completes the procedure by providing automatic camera-laser calibration. The procedure has been verified by extensive experimental tests with the proposed algorithms providing a major reduction in time required from an operator in comparison to manual methods.

Local inter-session variability modelling for object classification

Object classification is plagued by the issue of session variation. Session variation describes any variation that makes one instance of an object look different to another, for instance due to pose or illumination variation. Recent work in the challenging task of face verification has shown that session variability modelling provides a mechanism to overcome some of these limitations. However, for computer vision purposes, it has only been applied in the limited setting of face verification. In this paper we propose a local region based intersession variability (ISV) modelling approach, and apply it to challenging real-world data. We propose a region based session variability modelling approach so that local session variations can be modelled, termed Local ISV. We then demonstrate the efficacy of this technique on a challenging real-world fish image database which includes images taken underwater, providing significant real-world session variations. This Local ISV approach provides a relative performance improvement of, on average, 23% on the challenging MOBIO, Multi-PIE and SCface face databases. It also provides a relative performance improvement of 35% on our challenging fish image dataset.