Evaluation of two-view geometry methods with automatic ground-truth generation

A large number of methods have been published that aim to evaluate various components of multi-view geometry systems. Most of these have focused on the feature extraction, description and matching stages (the visual front end), since geometry computation can be evaluated through simulation. Many data sets are constrained to small scale scenes or planar scenes that are not challenging to new algorithms, or require special equipment. This paper presents a method for automatically generating geometry ground truth and challenging test cases from high spatio-temporal resolution video. The objective of the system is to enable data collection at any physical scale, in any location and in various parts of the electromagnetic spectrum. The data generation process consists of collecting high resolution video, computing accurate sparse 3D reconstruction, video frame culling and down sampling, and test case selection. The evaluation process consists of applying a test 2-view geometry method to every test case and comparing the results to the ground truth. This system facilitates the evaluation of the whole geometry computation process or any part thereof against data compatible with a realistic application. A collection of example data sets and evaluations is included to demonstrate the range of applications of the proposed system.

Crowd Counting Using Multiple Local Features

In public venues, crowd size is a key indicator of crowd safety and stability. Crowding levels can be detected using holistic image features, however this requires a large amount of training data to capture the wide variations in crowd distribution. If a crowd counting algorithm is to be deployed across a large number of cameras, such a large and burdensome training requirement is far from ideal. In this paper we propose an approach that uses local features to count the number of people in each foreground blob segment, so that the total crowd estimate is the sum of the group sizes. This results in an approach that is scalable to crowd volumes not seen in the training data, and can be trained on a very small data set. As a local approach is used, the proposed algorithm can easily be used to estimate crowd density throughout different regions of the scene and be used in a multi-camera environment. A unique localised approach to ground truth annotation reduces the required training data is also presented, as a localised approach to crowd counting has different training requirements to a holistic one. Testing on a large pedestrian database compares the proposed technique to existing holistic techniques and demonstrates improved accuracy, and superior performance when test conditions are unseen in the training set, or a minimal training set is used.

Dynamic Performance Measures for Object Tracking Systems

Performance evaluation of object tracking systems is typically performed after the data has been processed, by comparing tracking results to ground truth. Whilst this approach is fine when performing offline testing, it does not allow for real-time analysis of the systems performance, which may be of use for live systems to either automatically tune the system or report reliability. In this paper, we propose three metrics that can be used to dynamically asses the performance of an object tracking system. Outputs and results from various stages in the tracking system are used to obtain measures that indicate the performance of motion segmentation, object detection and object matching. The proposed dynamic metrics are shown to accurately indicate tracking errors when visually comparing metric results to tracking output, and are shown to display similar trends to the ETISEO metrics when comparing different tracking configurations.

Evaluation of aerial remote sensing techniques for vegetation management in power line corridors

The following paper presents an evaluation of airborne sensors for use in vegetation management in powerline corridors. Three integral stages in the management process are addressed including, the detection of trees, relative positioning with respect to the nearest powerline and vegetation height estimation. Image data, including multi-spectral and high resolution, are analyzed along with LiDAR data captured from fixed wing aircraft. Ground truth data is then used to establish the accuracy and reliability of each sensor thus providing a quantitative comparison of sensor options. Tree detection was achieved through crown delineation using a Pulse-Coupled Neural Network (PCNN) and morphologic reconstruction applied to multi-spectral imagery. Through testing it was shown to achieve a detection rate of 96%, while the accuracy in segmenting groups of trees and single trees correctly was shown to be 75%. Relative positioning using LiDAR achieved a RMSE of 1.4m and 2.1m for cross track distance and along track position respectively, while Direct Georeferencing achieved RMSE of 3.1m in both instances. The estimation of pole and tree heights measured with LiDAR had a RMSE of 0.4m and 0.9m respectively, while Stereo Matching achieved 1.5m and 2.9m. Overall a small number of poles were missed with detection rates of 98% and 95% for LiDAR and Stereo Matching.

Omnidirectional visual odometry for a planetary rover

Position estimation for planetary rovers has been typically limited to odometry based on proprioceptive measurements such as the integration of distance traveled and measurement of heading change. Here we present and compare two methods of online visual odometry suited for planetary rovers. Both methods use omnidirectional imagery to estimate motion of the rover. One method is based on robust estimation of optical flow and subsequent integration of the flow. The second method is a full structure-from-motion solution. To make the comparison meaningful we use the same set of raw corresponding visual features for each method. The dataset is an sequence of 2000 images taken during a field experiment in the Atacama desert, for which high resolution GPS ground truth is available.

Visual localisation in outdoor industrial building environments

This paper presents a vision-based method of vehicle localisation that has been developed and tested on a large forklift type robotic vehicle which operates in a mainly outdoor industrial setting. The localiser uses a sparse 3D edgemap of the environment and a particle filter to estimate the pose of the vehicle. The vehicle operates in dynamic and non-uniform outdoor lighting conditions, an issue that is addressed by using knowledge of the scene to intelligently adjust the camera exposure and hence improve the quality of the information in the image. Results from the industrial vehicle are shown and compared to another laser-based localiser which acts as a ground truth. An improved likelihood metric, using peredge calculation, is presented and has shown to be 40% more accurate in estimating rotation. Visual localization results from the vehicle driving an arbitrary 1.5km path during a bright sunny period show an average position error of 0.44m and rotation error of 0.62deg.

Further results with localization and mapping using range from radio

In this paper, we present recent results with using range from radio for mobile robot localization. In previous work we have shown how range readings from radio tags placed in the environment can be used to localize a robot. We have extended previous work to consider robustness. Specifically, we are interested in the case where range readings are very noisy and available intermittently. Also, we consider the case where the location of the radio tags is not known at all ahead of time and must be solved for simultaneously along with the position of the moving robot. We present results from a mobile robot that is equipped with GPS for ground truth, operating over several km.

Accurate silhouettes for surveillance : improved motion segmentation using graph cuts

Silhouettes are common features used by many applications in computer vision. For many of these algorithms to perform optimally, accurately segmenting the objects of interest from the background to extract the silhouettes is essential. Motion segmentation is a popular technique to segment moving objects from the background, however such algorithms can be prone to poor segmentation, particularly in noisy or low contrast conditions. In this paper, the work of [3] combining motion detection with graph cuts, is extended into two novel implementations that aim to allow greater uncertainty in the output of the motion segmentation, providing a less restricted input to the graph cut algorithm. The proposed algorithms are evaluated on a portion of the ETISEO dataset using hand segmented ground truth data, and an improvement in performance over the motion segmentation alone and the baseline system of [3] is shown.

Crowd counting using group tracking and local features

In public venues, crowd size is a key indicator of crowd safety and stability. In this paper we propose a crowd counting algorithm that uses tracking and local features to count the number of people in each group as represented by a foreground blob segment, so that the total crowd estimate is the sum of the group sizes. Tracking is employed to improve the robustness of the estimate, by analysing the history of each group, including splitting and merging events. A simplified ground truth annotation strategy results in an approach with minimal setup requirements that is highly accurate.

Application of K-tree to document clustering

Digital collections are growing exponentially in size as the information age takes a firm grip on all aspects of society. As a result Information Retrieval (IR) has become an increasingly important area of research. It promises to provide new and more effective ways for users to find information relevant to their search intentions. Document clustering is one of the many tools in the IR toolbox and is far from being perfected. It groups documents that share common features. This grouping allows a user to quickly identify relevant information. If these groups are misleading then valuable information can accidentally be ignored. There- fore, the study and analysis of the quality of document clustering is important. With more and more digital information available, the performance of these algorithms is also of interest. An algorithm with a time complexity of O(n2) can quickly become impractical when clustering a corpus containing millions of documents. Therefore, the investigation of algorithms and data structures to perform clustering in an efficient manner is vital to its success as an IR tool. Document classification is another tool frequently used in the IR field. It predicts categories of new documents based on an existing database of (doc- ument, category) pairs. Support Vector Machines (SVM) have been found to be effective when classifying text documents. As the algorithms for classifica- tion are both efficient and of high quality, the largest gains can be made from improvements to representation. Document representations are vital for both clustering and classification. Representations exploit the content and structure of documents. Dimensionality reduction can improve the effectiveness of existing representations in terms of quality and run-time performance. Research into these areas is another way to improve the efficiency and quality of clustering and classification results. Evaluating document clustering is a difficult task. Intrinsic measures of quality such as distortion only indicate how well an algorithm minimised a sim- ilarity function in a particular vector space. Intrinsic comparisons are inherently limited by the given representation and are not comparable between different representations. Extrinsic measures of quality compare a clustering solution to a “ground truth” solution. This allows comparison between different approaches. As the “ground truth” is created by humans it can suffer from the fact that not every human interprets a topic in the same manner. Whether a document belongs to a particular topic or not can be subjective.

Unaided stereo vision based pose estimation

This paper presents the development of a low-cost sensor platform for use in ground-based visual pose estimation and scene mapping tasks. We seek to develop a technical solution using low-cost vision hardware that allows us to accurately estimate robot position for SLAM tasks. We present results from the application of a vision based pose estimation technique to simultaneously determine camera poses and scene structure. The results are generated from a dataset gathered traversing a local road at the St Lucia Campus of the University of Queensland. We show the accuracy of the pose estimation over a 1.6km trajectory in relation to GPS ground truth.

Graphcut-based interactive segmentation using colour and depth cues

Segmentation of novel or dynamic objects in a scene, often referred to as background sub- traction or foreground segmentation, is critical for robust high level computer vision applica- tions such as object tracking, object classifca- tion and recognition. However, automatic real- time segmentation for robotics still poses chal- lenges including global illumination changes, shadows, inter-re ections, colour similarity of foreground to background, and cluttered back- grounds. This paper introduces depth cues provided by structure from motion (SFM) for interactive segmentation to alleviate some of these challenges. In this paper, two prevailing interactive segmentation algorithms are com- pared; Lazysnapping [Li et al., 2004] and Grab- cut [Rother et al., 2004], both based on graph- cut optimisation [Boykov and Jolly, 2001]. The algorithms are extended to include depth cues rather than colour only as in the original pa- pers. Results show interactive segmentation based on colour and depth cues enhances the performance of segmentation with a lower er- ror with respect to ground truth.

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.

Towards automated and in-situ, near-real time 3-D reconstruction of coral reef environments

Coral reefs are biologically complex ecosystems that support a wide variety of marine organisms. These are fragile communities under enormous threat from natural and human-based influences. Properly assessing and measuring the growth and health of reefs is essential to understanding impacts of ocean acidification, coastal urbanisation and global warming. In this paper, we present an innovative 3-D reconstruction technique based on visual imagery as a non-intrusive, repeatable, in situ method for estimating physical parameters, such as surface area and volume for efficient assessment of long-term variability. The reconstruction algorithms are presented, and benchmarked using an existing data set. We validate the technique underwater, utilising a commercial-off-the-shelf camera and a piece of staghorn coral, Acropora cervicornis. The resulting reconstruction is compared with a laser scan of the coral piece for assessment and validation. The comparison shows that 77% of the pixels in the reconstruction are within 0.3 mm of the ground truth laser scan. Reconstruction results from an unknown video camera are also presented as a segue to future applications of this research.

Evaluation of texture and geometry for dimensional facial expression recognition

Facial expression recognition (FER) algorithms mainly focus on classification into a small discrete set of emotions or representation of emotions using facial action units (AUs). Dimensional representation of emotions as continuous values in an arousal-valence space is relatively less investigated. It is not fully known whether fusion of geometric and texture features will result in better dimensional representation of spontaneous emotions. Moreover, the performance of many previously proposed approaches to dimensional representation has not been evaluated thoroughly on publicly available databases. To address these limitations, this paper presents an evaluation framework for dimensional representation of spontaneous facial expressions using texture and geometric features. SIFT, Gabor and LBP features are extracted around facial fiducial points and fused with FAP distance features. The CFS algorithm is adopted for discriminative texture feature selection. Experimental results evaluated on the publicly accessible NVIE database demonstrate that fusion of texture and geometry does not lead to a much better performance than using texture alone, but does result in a significant performance improvement over geometry alone. LBP features perform the best when fused with geometric features. Distributions of arousal and valence for different emotions obtained via the feature extraction process are compared with those obtained from subjective ground truth values assigned by viewers. Predicted valence is found to have a more similar distribution to ground truth than arousal in terms of covariance or Bhattacharya distance, but it shows a greater distance between the means.