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.

Human Foot Reconstruction from Multiple Camera Images with Foot Shape Database

Abstract: Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera images, which can capture dynamic behavior of the object. In this paper, a foot-shape database is used for accurate reconstruction of human foot. By using Principal Component Analysis, the foot shape can be represented with new meaningful variables. The dimensionality of the data is also reduced. Thus, the shape of object can be recovered efficiently, even though the object is partially occluded in some input views. To demonstrate the proposed method, two kinds of experiments are presented: reconstruction of human foot in a virtual reality environment with CG multi-camera images, and in real world with eight CCD cameras. In the experiments, the reconstructed shape error with our method is around 2 mm in average, while the error is more than 4 mm with conventional volume intersection method.

Multiaperture telecentric lens for 3D reconstruction

Abstract: We present a telecentric lens that is able to gain 3D information. The proposed lens system has multiple aperture stops, which enable it to capture multidirectional parallel light rays, while a conventional telecentric lens has only one aperture stop and can capture only light rays that are perpendicular to the lens. We explain the geometry of the multiaperture telecentric system and show that correspondences fall on a line like those in a conventional stereo. As it is a single-lens sensor, we also introduce the principles of 3D reconstruction. Unlike a conventional stereo camera, the disparity of a scene point measured by the proposed lens system is linearly proportional to the depth of a scene point.

Extracting topographic features for outdoor mobile robots

Abstract: Methods are presented for building high-level terrain descriptions, referred 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. The authors develop new definitions for those topographic features based on the contour map. They build a contour map from an elevation map and generate the connectivity tree of all regions separated by the contours. The authors use this connectivity tree, called a topographic change tree, to extract the topographic features. Experimental results on a digital elevation model support the definitions for topographic features and the approach. >

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.