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.

When is the shape of a scene unique given its light-field: a fundamental theorem of 3D vision?

Abstract: The complete set of measurements that could ever be used by a passive 3D vision algorithm is the plenoptic function or light-field. We give a concise characterization of when the light-field of a Lambertian scene uniquely determines its shape and, conversely, when the shape is inherently ambiguous. In particular, we show that stereo computed from the light-field is ambiguous if and only if the scene is radiating light of a constant intensity (and color, etc.) over an extended region.

System and method for obtaining video of multiple moving fixation points within a dynamic scene

Abstract: A system and method for obtaining video of a moving fixation point within a scene. According to one embodiment, the system includes a control unit and a plurality of non-moving image capturing devices positioned around the scene, wherein the scene is within a field of view of each image capturing device. The system also includes a plurality of image generators, wherein each image generator is in communication with one of the image capturing devices, and wherein a first of the image generators is responsive to a command from the control unit. The system also includes a surround-view image sequence generator in communication with each of the image generators and responsive to the command form the control unit for generating a surround-view video sequence of the fixation point within the scene based on output form certain of the image generators.

Post-Operative Measurement of Acetabular Cup Position Using X-Ray/CT Registration

Abstract: This paper describes a system for measuring acetabular implant orientation following total hip replacement surgery. After a manual initialization procedure, the position of the pelvis is established relative to a pair of nearly orthogonal radiographs by automatically registering to pre-operative pelvic CT data. The pose of the cup is then recovered by projecting a 3D surface model into the two images. A phantom study is presented in which this pose is expressed relative to well defined anatomical landmarks and compared to measurements obtained using an image-guided surgery system.

Apoptosis detection for adherent cell populations in time-lapse phase-contrast microscopy images

Abstract: The detection of apoptosis, or programmed cell death, is important to understand the underlying mechanism of cell development. At present, apoptosis detection resorts to fluorescence or colorimetric assays, which may affect cell behavior and thus not allow long-term monitoring of intact cells. In this work, we present an image analysis method to detect apoptosis in time-lapse phase-contrast microscopy, which is non-destructive imaging. The method first detects candidates for apoptotic cells based on the optical principle of phase-contrast microscopy in connection with the properties of apoptotic cells. The temporal behavior of each candidate is then examined in its neighboring frames in order to determine if the candidate is indeed an apoptotic cell. When applied to three C2C12 myoblastic stem cell populations, which contain more than 1000 apoptosis, the method achieved around 90% accuracy in terms of average precision and recall.

Ambler: a six-legged planetary rover

Abstract: The goal of the planetary rover project is to prototype an autonomous mobile robot for planetary exploration. The authors have constructed a six-legged walking robot, called the Ambler, that features orthogonal legs, an overlapping gait, and a scanning laser rangefinder to model terrain. To enable the Ambler to walk over rugged terrain, they have combined perception, planning, and real-time control into a comprehensive robotic system. >

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.