Parameter Sensitive Detectors

Object detection can be challenging when the object class exhibits large variations. One commonly-used strategy is to first partition the space of possible object variations and then train separate classifiers for each portion. However, with continuous spaces the partitions tend to be arbitrary since there are no natural boundaries (for example, consider the continuous range of human body poses). In this paper, a new formulation is proposed, where the detectors themselves are associated with continuous parameters, and reside in a parameterized function space. There are two advantages of this strategy. First, a-priori partitioning of the parameter space is not needed; the detectors themselves are in a parameterized space. Second, the underlying parameters for object variations can be learned from training data in an unsupervised manner. In profile face detection experiments, at a fixed false alarm number of 90, our method attains a detection rate of 75% vs. 70% for the method of Viola-Jones. In hand shape detection, at a false positive rate of 0.1%, our method achieves a detection rate of 99.5% vs. 98% for partition based methods. In pedestrian detection, our method reduces the miss detection rate by a factor of three at a false positive rate of 1%, compared with the method of Dalal-Triggs.

Learning a Family of Detectors

Object detection and recognition are important problems in computer vision. The challenges of these problems come from the presence of noise, background clutter, large within class variations of the object class and limited training data. In addition, the computational complexity in the recognition process is also a concern in practice. In this thesis, we propose one approach to handle the problem of detecting an object class that exhibits large within-class variations, and a second approach to speed up the classification processes. In the first approach, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly solved with using a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. For applications where explicit parameterization of the within-class states is unavailable, a nonparametric formulation of the kernel can be constructed with a proper foreground distance/similarity measure. Detector training is accomplished via standard Support Vector Machine learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the image masks for foreground objects are provided in training, the detectors can also produce object segmentation. Methods for generating a representative sample set of detectors are proposed that can enable efficient detection and tracking. In addition, because individual detectors verify hypotheses of foreground state, they can also be incorporated in a tracking-by-detection frame work to recover foreground state in image sequences. To run the detectors efficiently at the online stage, an input-sensitive speedup strategy is proposed to select the most relevant detectors quickly. The proposed approach is tested on data sets of human hands, vehicles and human faces. On all data sets, the proposed approach achieves improved detection accuracy over the best competing approaches. In the second part of the thesis, we formulate a filter-and-refine scheme to speed up recognition processes. The binary outputs of the weak classifiers in a boosted detector are used to identify a small number of candidate foreground state hypotheses quickly via Hamming distance or weighted Hamming distance. The approach is evaluated in three applications: face recognition on the face recognition grand challenge version 2 data set, hand shape detection and parameter estimation on a hand data set, and vehicle detection and estimation of the view angle on a multi-pose vehicle data set. On all data sets, our approach is at least five times faster than simply evaluating all foreground state hypotheses with virtually no loss in classification accuracy.

Development of a GEM Electronic Board (GEB) for triple-GEM detectors

Developed for use with triple GEM detectors, the GEM Electronic Board (GEB) forms a crucial part of the electronics readout system being developed as part of the CMS muon upgrade program. The objective of the GEB is threefold; to provide stable powering and ground for the VFAT3 front ends, to enable high-speed communication between 24 VFAT3 front ends and an optohybrid, and to shield the GEM detector from electromagnetic interference. The paper describes the concept and design of a large-size GEB in detail, highlighting the challenges in terms of design and feasibility of this deceptively difficult system component.

Hormesis - Stimulation Of Colony Growth In Campanularia-Flexuosa (Hydrozoa) By Copper Cadmium And Other Toxicants

It is shown experimentally that subinhibitory concentrations of a number of toxic, or other agents that are typically inhibitory (copper, cadmium, tributyl tin fluoride, reduced salinity), may stimulate the growth of colonies of the hydroid Campanularia flexuosa, exhibiting a phenomenon known as hormesis. It is suggested that the stimulation of growth is not due to the specific properties of the different toxicants, but to an adaptive response of the hydroid to the inhibitory effect that they have in common. Growth is regulated by a control mechanism and it is proposed that the increased growth is a consequence of overcorrections to low levels of an inhibitory challenge. Examination of the toxicological literature shows that hormesis is a more common occurrence that is generally supposed, and it is suggested that the explanation given here might apply in other cases of hormesis.

Simulating The Impact Of Technological-Change On Dissolved Cadmium Distribution In The Severn Estuary

An estuarine model is described which computes the dispersive and advective properties of the Severn Estuary. It was calibrated and validated using 50 measured salinity distributions and then used to predict the magnitude and sitings of the major inputs of dissolved cadmium levels throughout the estuary. The results provided an impetus for implementing tighter controls on effluents and for improving estimates of cadmium discharges from industrial sources. The model has also been used to investigate the sensitivity of the estuarine system to changes in dispersion; by considering large reductions in the dispersion coefficients it is hoped that the results might be indicative of the environmental consequences following the construction of a tidal power generating scheme.