Learn More
We propose a space-time Markov random field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activity at each local node, we capture the distribution of its typical(More)
We present an approach to discover and segment foreground object(s) in video. Given an unannotated video sequence, the method first identifies object-like regions in any frame according to both static and dynamic cues. We then compute a series of binary partitions among those candidate “key-segments” to discover hypothesis groups with(More)
We introduce a fast deformable spatial pyramid (DSP) matching algorithm for computing dense pixel correspondences. Dense matching methods typically enforce both appearance agreement between matched pixels as well as geometric smoothness between neighboring pixels. Whereas the prevailing approaches operate at the pixel level, we propose a pyramid graph model(More)
We introduce a category-independent shape prior for object segmentation. Existing shape priors assume class-specific knowledge, and thus are restricted to cases where the object class is known in advance. The main insight of our approach is that shapes are often shared between objects of different categories. To exploit this “shape sharing” phenomenon, we(More)
We propose a dense local region detector to extract features suitable for image matching and object recognition tasks. Whereas traditional local interest operators rely on repeatable structures that often cross object boundaries (e.g., corners, scale-space blobs), our sampling strategy is driven by segmentation, and thus preserves object boundaries and(More)
We present a feature matching algorithm that leverages bottom-up segmentation. Unlike conventional image-to-image or region-to-region matching algorithms, our method finds corresponding points in an “asymmetric” manner, matching features within each region of a segmented image to a second unsegmented image. We develop a dynamic programming(More)
PEAKSAVE system is an energy monitoring service based on Wireless Sensor Networks (WSN). A smartphone is an important point of a system. Users can understand the energy consumption of each electric device and lighting in real time. Responsive energy monitoring service can help in reducing the waste of energy, especially in shaving electric load in a peak(More)
Algorithm 1 gives the procedure used to optimize the background motion model as described in Section 4. GetWeights computes the residuals from the given model Hk and uses Equation 3 to compute the weight for each track in T . Similarly, GetCost computes the total cost (Equation 4). Finally, WLS uses a weighted-least-squares variant of the four-point(More)