A saliency-based target detection method for forward looking infrared (FLIR) image is proposed. Firstly, saliency map is computed using scale-space representation and separated into dark saliency map (DSM) and bright ...
详细信息
A saliency-based target detection method for forward looking infrared (FLIR) image is proposed. Firstly, saliency map is computed using scale-space representation and separated into dark saliency map (DSM) and bright saliency map (BSM). Secondly, dark and bright regions of interest (ROI) are detected by respective type of saliency map using marker-based maximally stable extremal regions (MSER) detection algorithm. Finally, shape matching algorithm is applied after grouping of the two types of ROI for object detection. Experimental results show that this work provides a promising way to solve the problems caused by salient dark parts of target.
This paper proposes a novel weighted template matching method. It employs a generalized distance transform (GDT) and an orientation map (OM). The GDT allows us to weight the distance transform more on the strong edge ...
详细信息
This paper proposes a novel weighted template matching method. It employs a generalized distance transform (GDT) and an orientation map (OM). The GDT allows us to weight the distance transform more on the strong edge points and the OM provides supplementary local orientation information for matching. Based on the matching method, a two-stage human detection method consisting of template matching and Bayesian verification is developed. Experimental results have shown that the proposed method can effectively reduce the false positive and false negative detection rates and perform superiorly in comparison to the conventional Chamfer matching method.
Rock fractures junctions are important objects for detection of rock fracture. Traditionally, junction detectors are devoted to the step-edge corners. Such corners are usually located using a Laplascian operator (zero...
详细信息
Rock fractures junctions are important objects for detection of rock fracture. Traditionally, junction detectors are devoted to the step-edge corners. Such corners are usually located using a Laplascian operator (zero-crossings or extrema) or a curvature measure based on the gradient direction. However, the gradient direction of a line does not exist, and a line junction does not correspond to a zero-crossing of the Laplacian. Consequently, step-edge corner detectors are not suitable for line junctions. Their response to a single line junction is not unique. There are other methods to detect the junction. Most of them find L-shaped corners, but create multiple or no responses for more complex junctions. This paper proposes a robust detection method for gray-level line junction which is called the neighborhood pixel-track algorithm. Examples are provided based on experiments with synthetic and real images. The achieved results demonstrate that such junction detection algorithm can successfully identify T-and Y-junctions, and of degree four X-junctions or more complex intercross of rock fractures.
This paper considers a simple on-off random multiple access channel (MAC), where n users communicate simultaneously to a single receiver. Each user is assigned a single codeword which it transmits with some probabilit...
详细信息
This paper considers a simple on-off random multiple access channel (MAC), where n users communicate simultaneously to a single receiver. Each user is assigned a single codeword which it transmits with some probability lambda over m degrees of freedom. The receiver must detect which users transmitted. We show that detection for this random MAC is mathematically equivalent to a standard sparsity detection problem. Using new results in sparse estimation we are able to estimate the capacity of these channels and compare the achieved performance of various detection algorithms. The analysis provides insight into the roles of power control and multi-user detection.
In this study, a video shot boundary detection algorithm based on the dominant sets concept is proposed. Dominant sets method is a graph theoretic clustering algorithm. Proposed method is based on a weighted undirecte...
详细信息
In this study, a video shot boundary detection algorithm based on the dominant sets concept is proposed. Dominant sets method is a graph theoretic clustering algorithm. Proposed method is based on a weighted undirected graph. Candidate shot boundaries are determined and graphs are constructed by taking 2 frames from the right of the candidate position and 4 frames from the left of the candidate position. Edge weights among the vertices are evaluated by using pairwise similarities of frames. By using the complete information of the graph, a set of the vertices mostly similar to each other and dissimilar to the others is detected. True cut positions are determined if the dominant set includes the 4 frames before the candidate position. The simulation results indicate that the proposed algorithm can be used for abrupt shot boundary detection.
A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing. A ...
详细信息
A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing. A postprocessing scheme is developed from the probability of seizure estimate in order to improve the performance of the system. Results are reported on a dataset of 17 patients with a total duration of 267.9 hours, the average ROC area of the system is 95.6%.
This paper proposes a frontal staircase detection algorithm using both classical Haar-like features and a novel set of PCA-base Haar-like features. Real AdaBoost is used for training a cascaded classifier. The PCA-bas...
详细信息
ISBN:
(纸本)9781424446568
This paper proposes a frontal staircase detection algorithm using both classical Haar-like features and a novel set of PCA-base Haar-like features. Real AdaBoost is used for training a cascaded classifier. The PCA-based Haar-like features are extremely efficient at rejecting background regions at early stages in the cascade. A specifically designed scanning scheme made the algorithm constantly time efficient to different image sizes. An multi-detections integration scheme that is exclusive for staircase detection is extremely useful at further rejecting false positives. A new evaluation metric is proposed to rate each final detection, instead of Boolean classifying it. Experimental results show that the approach can detect staircases accurately at extremely low false positive rate.
Maximum-likelihood detection (MLD) is the optimal scheme for vertical Bell Laboratories layered space-time (V-BLAST) systems. However, due to its exponentially high complexity, many alternative algorithms, including s...
详细信息
Maximum-likelihood detection (MLD) is the optimal scheme for vertical Bell Laboratories layered space-time (V-BLAST) systems. However, due to its exponentially high complexity, many alternative algorithms, including some parallel detection (PD) ones with low complexity and high stability, have been proposed instead for practical applications. Nevertheless, the existing PD algorithms are unable to exploit sufficiently the diversity order increment for low-complexity algorithms via exhaustive interference cancellation (EIC) and the complexity of the sub-detectors is still undesirably high. In this paper, a novel PD algorithm with relative low-complexity sub-detectors, i.e., the selective-interference-cancellation sub-detectors, has been developed. The algorithm is abbreviated as PDSIC algorithm. Numerical analysis indicates that the PDSIC algorithm can achieve the near-optimal performance with much lower complexity in comparison with the existing PD algorithms. Thus, the PDSIC algorithm makes the parallel detection more feasible in practical systems with limited parallel processing elements.
Vertical Bell-laboratories Space-Time (V-BLAST) is a multiple transmit and multiple receive antennas (MIMO) wireless systems. V-BLAST attains very high spectral efficiency while maintaining low implementation complexi...
详细信息
Vertical Bell-laboratories Space-Time (V-BLAST) is a multiple transmit and multiple receive antennas (MIMO) wireless systems. V-BLAST attains very high spectral efficiency while maintaining low implementation complexity. Among the detection algorithms of V-BLAST, Maximum Likelihood (ML) detection scheme performs the best, and however, its complexity is excessively high. To solve the problem, a reduced complexity ML detection algorithm is proposed in this paper. This scheme takes advantage of OSIC detection algorithm to reduce the number of constellation point in ML detection. Simulation results show that the proposed scheme reduces the computational complexity greatly and achieves high detection performance which is close to ML detection.
A neural network (NN)-based technique making direct use of measured dynamic responses in civil structures is proposed to model the structure and detect eventual anomalies with their location and extent. Although numer...
详细信息
ISBN:
(纸本)9781424452095
A neural network (NN)-based technique making direct use of measured dynamic responses in civil structures is proposed to model the structure and detect eventual anomalies with their location and extent. Although numerous researches were conducted to apply NN for damage detection purposes, the problem constituted by the selection of an appropriate architecture for the networks still remains a major obstacle impeding their applicability. In order to avoid this shortcoming, the proposed algorithm performs the modeling of the structure stepwise by successive integration-like neural operations, which permits to reduce effectively the size of the networks and simplify effectively their architecture. The damage parameter is decided to be the restoring forces and corresponding stiffness of each major structural member. The trained network fed with data of the structure encountering diverse damage events under various loading episodes reconstructs the actual restoring force loops and the ones that should be obtained for the undamaged structure, of which comparison provides accurate estimation of damages. A shear building example verifies the efficiency and accuracy of the proposed method in detecting, locating and giving the extent of damages in real time.
暂无评论