Takeo Kanade

Bio: Takeo Kanade is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Motion estimation & Image processing. The author has an hindex of 147, co-authored 799 publications receiving 103237 citations. Previous affiliations of Takeo Kanade include National Institute of Advanced Industrial Science and Technology & Hitachi.

Mode-seeking by Medoidshifts

Abstract: We present a nonparametric mode-seeking algorithm, called medoidshift, based on approximating the local gradient using a weighted estimate of medoids. Like meanshift, medoidshift clustering automatically computes the number of clusters and the data does not have to be linearly separable. Unlike meanshift, the proposed algorithm does not require the definition of a mean. This property allows medoidshift to find modes even when only a distance measure between samples is defined. In this sense, the relationship between the medoidshift algorithm and the meanshift algorithm is similar to the relationship between the k-medoids and the k-means algorithms. We show that medoidshifts can also be used for incremental clustering of growing datasets by recycling previous computations. We present experimental results using medoidshift for image segmentation, incremental clustering for shot segmentation and clustering on nonlinearly separable data.

Extracting topographic terrain features from elevation maps

Abstract: Some applications such as the autonomous navigation in natural terrain and the automation of map making process require highlevel scene descriptions as well as geometrical representation of the natural terrain environments. In this paper, we present methods for building high level terrain descriptions, referred to as topographic maps, by extracting terrain features like “peaks,” “pits,” “ridges,” and “ravines” from the contour map. The resulting topographic map contains the location and type of terrain features as well as the ground topography. We present new algorithms for extracting topographic maps consisting of topographic features (peaks, pits, ravines, and ridges) and contour maps. We develop new definitions for those topographic features based on the contour map. We build a contour map from an elevation map and generate the connectivity tree of all regions separated by the contours. We use this connectivity tree, called a topographic change tree, to extract the topographic features. Experimental results on a digital elevation model (DEM) supports our definitions for topographic features and the approach. D 1994 Academic prss, Inc.

Shape-From-Silhouette Across Time Part II: Applications to Human Modeling and Markerless Motion Tracking

Abstract: In Part I of this paper we developed the theory and algorithms for performing Shape-From-Silhouette (SFS) across time. In this second part, we show how our temporal SFS algorithms can be used in the applications of human modeling and markerless motion tracking. First we build a system to acquire human kinematic models consisting of precise shape (constructed using the temporal SFS algorithm for rigid objects), joint locations, and body part segmentation (estimated using the temporal SFS algorithm for articulated objects). Once the kinematic models have been built, we show how they can be used to track the motion of the person in new video sequences. This marker-less tracking algorithm is based on the Visual Hull alignment algorithm used in both temporal SFS algorithms and utilizes both geometric (silhouette) and photometric (color) information.

A multibaseline stereo system with active illumination and real-time image acquisition

Abstract: We describe our implementation of a parallel depth recovery scheme for a four-camera multibaseline stereo in a convergent configuration. Our system is capable of image capture at video rate. This is critical in applications that require three-dimensional tracking. We obtain dense stereo depth data by projecting a light pattern of frequency modulated sinusoidally varying intensity onto the scene, thus increasing the local discriminability at each pixel and facilitating matches. In addition, we make most of the camera view areas by converging them at a volume of interest. Results show that we are able to extract stereo depth data that are, on the average, less than 1 mm in error at distances between 1.5 to 3.5 m away from the cameras. >

Gradient-based learning applied to document recognition

Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Going deeper with convolutions

Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Histograms of oriented gradients for human detection

Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.