A convolutional neural network for automatic analysis of aerial imagery

This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.

Score-level multibiometric fusion based on Dempster-Shafer theory incorporating uncertainty factors

While existing multi-biometic Dempster-Shafer the- ory fusion approaches have demonstrated promising perfor- mance, they do not model the uncertainty appropriately, sug- gesting that further improvement can be achieved. This research seeks to develop a unified framework for multimodal biometric fusion to take advantage of the uncertainty concept of Dempster- Shafer theory, improving the performance of multi-biometric authentication systems. Modeling uncertainty as a function of uncertainty factors affecting the recognition performance of the biometric systems helps to address the uncertainty of the data and the confidence of the fusion outcome. A weighted combination of quality measures and classifiers performance (Equal Error Rate) are proposed to encode the uncertainty concept to improve the fusion. We also found that quality measures contribute unequally to the recognition performance, thus selecting only significant factors and fusing them with a Dempster-Shafer approach to generate an overall quality score play an important role in the success of uncertainty modeling. The proposed approach achieved a competitive performance (approximate 1% EER) in comparison with other Dempster-Shafer based approaches and other conventional fusion approaches.

Large-scale analysis of soccer matches using spatiotemporal tracking data

Although the collection of player and ball tracking data is fast becoming the norm in professional sports, large-scale mining of such spatiotemporal data has yet to surface. In this paper, given an entire season's worth of player and ball tracking data from a professional soccer league (approx 400,000,000 data points), we present a method which can conduct both individual player and team analysis. Due to the dynamic, continuous and multi-player nature of team sports like soccer, a major issue is aligning player positions over time. We present a "role-based" representation that dynamically updates each player's relative role at each frame and demonstrate how this captures the short-term context to enable both individual player and team analysis. We discover role directly from data by utilizing a minimum entropy data partitioning method and show how this can be used to accurately detect and visualize formations, as well as analyze individual player behavior.

Identifying team style in soccer using formations learned from spatiotemporal tracking data

To the trained-eye, experts can often identify a team based on their unique style of play due to their movement, passing and interactions. In this paper, we present a method which can accurately determine the identity of a team from spatiotemporal player tracking data. We do this by utilizing a formation descriptor which is found by minimizing the entropy of role-specific occupancy maps. We show how our approach is significantly better at identifying different teams compared to standard measures (i.e., shots, passes etc.). We demonstrate the utility of our approach using an entire season of Prozone player tracking data from a top-tier professional soccer league.

Visual predictive control of spiral motion

This paper deals with constrained image-based visual servoing of circular and conical spiral motion about an unknown object approximating a single image point feature. Effective visual control of such trajectories has many applications for small unmanned aerial vehicles, including surveillance and inspection, forced landing (homing), and collision avoidance. A spherical camera model is used to derive a novel visual-predictive controller (VPC) using stability-based design methods for general nonlinear model-predictive control. In particular, a quasi-infinite horizon visual-predictive control scheme is derived. A terminal region, which is used as a constraint in the controller structure, can be used to guide appropriate reference image features for spiral tracking with respect to nominal stability and feasibility. Robustness properties are also discussed with respect to parameter uncertainty and additive noise. A comparison with competing visual-predictive control schemes is made, and some experimental results using a small quad rotor platform are given.

BOSTER : an efficient algorithm for mining frequent unordered induced subtrees

Extracting frequent subtrees from the tree structured data has important applications in Web mining. In this paper, we introduce a novel canonical form for rooted labelled unordered trees called the balanced-optimal-search canonical form (BOCF) that can handle the isomorphism problem efficiently. Using BOCF, we define a tree structure guided scheme based enumeration approach that systematically enumerates only the valid subtrees. Finally, we present the balanced optimal search tree miner (BOSTER) algorithm based on BOCF and the proposed enumeration approach, for finding frequent induced subtrees from a database of labelled rooted unordered trees. Experiments on the real datasets compare the efficiency of BOSTER over the two state-of-the-art algorithms for mining induced unordered subtrees, HybridTreeMiner and UNI3. The results are encouraging.

BEST : an efficient algorithm for mining frequent unordered embedded subtrees

This paper presents an algorithm for mining unordered embedded subtrees using the balanced-optimal-search canonical form (BOCF). A tree structure guided scheme based enumeration approach is defined using BOCF for systematically enumerating the valid subtrees only. Based on this canonical form and enumeration technique, the balanced optimal search embedded subtree mining algorithm (BEST) is introduced for mining embedded subtrees from a database of labelled rooted unordered trees. The extensive experiments on both synthetic and real datasets demonstrate the efficiency of BEST over the two state-of-the-art algorithms for mining embedded unordered subtrees, SLEUTH and U3.

The UAV Challenge

The UAV challenge takes place every year. Teams of compteitors compete to use an Unmanned Airborne Vehicle to locate a simulated lost person and deliver water.

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.

Automated melanoma diagnosis system

An automated melanoma diagnosis system, the so-called Skin Polar-probe, was developed to improve the chances of early detection of skin cancers and help save the lives of melanoma victims. The system will offer unique benefits to aid early detection of melanoma - the key to reducing deaths caused by this cancer.

A Likelihood-Maximizing Framework for Enhanced In-Car Speech Recognition Based on Speech Dialog System Interaction

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating noncritical in-car systems. Under such conditions, however, speech recognition accuracy degrades significantly, and techniques such as speech enhancement are required to improve these accuracies. Likelihood-maximizing (LIMA) frameworks optimize speech enhancement algorithms based on recognized state sequences rather than traditional signal-level criteria such as maximizing signal-to-noise ratio. LIMA frameworks typically require calibration utterances to generate optimized enhancement parameters that are used for all subsequent utterances. Under such a scheme, suboptimal recognition performance occurs in noise conditions that are significantly different from that present during the calibration session – a serious problem in rapidly changing noise environments out on the open road. In this chapter, we propose a dialog-based design that allows regular optimization iterations in order to track the ever-changing noise conditions. Experiments using Mel-filterbank noise subtraction (MFNS) are performed to determine the optimization requirements for vehicular environments and show that minimal optimization is required to improve speech recognition, avoid over-optimization, and ultimately assist with semireal-time operation. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session only.

A Boundary-Oriented Chinese Segmentation Method Using NGram Mutual Information

This paper describes our participation in the Chinese word segmentation task of CIPS-SIGHAN 2010. We implemented an n-gram mutual information (NGMI) based segmentation algorithm with the mixed-up features from unsupervised, supervised and dictionarybased segmentation methods. This algorithm is also combined with a simple strategy for out-of-vocabulary (OOV) word recognition. The evaluation for both open and closed training shows encouraging results of our system. The results for OOV word recognition in closed training evaluation were however found unsatisfactory.

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.