In object detection, the cost of labeling is very high because it needs not only to confirm the categories of multiple objects in an image but also to determine the bounding boxes of each object accurately. Thus, integrating active learning into object detection will raise pretty positive significance. In this paper, we propose a classification committee for the active deep object detection method by introducing a discrepancy mechanism of multiple classifiers for samples' selection when training object detectors. The model contains a main detector and a classification committee. The main detector denotes the target object detector trained from a labeled pool composed of the selected informative images. The role of the classification committee is to select the most informative images according to their uncertainty values from the view of classification, which is expected to focus more on the discrepancy and representative of instances. Specifically, they compute the uncertainty for a specified instance within the image by measuring its discrepancy output by the committee pre-trained via the proposed Maximum Classifiers Discrepancy Group Loss (MCDGL). The most informative images are finally determined by selecting the ones with many high-uncertainty instances. Besides, to mitigate the impact of interference instances, we design a Focusing on Positive Instances Loss (FPIL) to provide the committee the ability to automatically focus on the representative instances as well as precisely encode their discrepancies for the same instance. Experiments are conducted on Pascal VOC and COCO datasets versus some popular object detectors. And results show that our method outperforms the state-of-the-art active learning methods, which verifies the effectiveness of the proposed method.

The authors present a local stereo matching algorithm whose performance is insensitive to changes in radiometric conditions between the input images. First, a prior on the disparities is built by combining the DAISY descriptor and Census filtering. Then, a Census‐based cost aggregation with a self‐adaptive window is performed. Finally, the maximum a‐posteriori estimation is carried out to compute the disparity. The authors’ algorithm is compared with both local and global stereo matching algorithms (NLCA, ELAS, ANCC, AdaptWeight and CSBP) by using Middlebury datasets. The results show that the proposed algorithm achieves high‐accuracy dense disparity estimations and is more robust to radiometric differences between input images than other algorithms.

Wireless sensor networks (WSNs) can provide real-time information about geospatial environments, and so have the potential to play an important role in the monitoring of geographic phenomena. The research reported in this paper uses WSNs to provide salient information about spatially distributed dynamic fields, such as regional variations in temperature or concentration of a toxic gas. The focus is on topological changes to areas of high-activity that occur during the evolution of the field. Topological changes investigated include region merging and splitting, and hole formation or elimination. Such changes are formally characterized, and an algorithm is developed that detects such changes by means purely of in-network processing. The efficiency of this algorithm is investigated both theoretically and using simulation experiments.

Program slicing is an available method that is widely used in program understanding, analyzing, debugging, testing, maintaining. There are many solutions for slicing procedural program and object-oriented program. But traditional slicing method usually based on PDG and SDG that is not suitable to a Web application because of Web's special characteristics. This paper suggests a kind of slicing method that use hyper graph to define dependency of elements named PDSG (program dependence hyper graph). PDSG can describe dependence of the Web elements better than PDG. This method also makes the slicing algorithm simpler and the slice captured is integrated in semantics.

Web applications have rapid developing speed and changeable user demands, so the regression testing is much important. Since the changed demands result in different versions of Web applications, and the faults usually hiding in the adjusted contents, the regression testing must cover all the related pages. In order to carry through the regression testing quickly and effectively, we make the simplification with the method of slicing. Firstly, we analyze the possible changes in the Web applications and the influences produced by these changes, discussing in the direct-dependent and indirect-dependent way; next, we give the regression testing method based on slicing emphasized on the indirect-dependent among data, i.e., obtaining the dependent set of changed variables by forward and backward search method and generating the testing suits; conclusion remarks and future work are given at last.