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.

“Virtual touch”: an efficient registration method for catheter navigation in left atrium

Abstract: In this paper, we present a left atrium registration system which utilizes a 3D intra-cardiac ultrasound catheter for faster (more than 700 times) and higher quality surface registration point collection than current systems and eventually improves the registration accuracy and stability With better registration our system can greatly improve the ablation catheter navigation system which is being used in many hospitals to guide left atrium endocardium ablation procedure

Research on an autonomous vision-guided helicopter

Abstract: Integration of computer vision with on-board sensors to autonomously fly helicopters was researched. The key components developed were custom designed vision processing hardware and an indoor testbed. The custom designed hardware provided flexible integration of on-board sensors with real-time image processing resulting in a significant improvement in vision-based state estimation. The indoor testbed provided convenient calibrated experimentation in constructing real autonomous systems.

A histogram-based method for detection of faces and cars

Abstract: We describe a statistical method for 3D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints.

Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction

Abstract: Geometric reconstruction problems in computer vision can be solved by minimizing the maximum of reprojection errors, i.e., the L\infty-norm. Unlike L2-norm (sum of squared reprojection errors), the global minimum of L\infty-norm can be efficiently achieved by quasiconvex optimization. However, the maximum of reprojection errors is the meaningful measure to minimize only when the measurement noises are independent and identically distributed at every 2D feature point and in both directions in the image. This is rarely the case in real data, where the positional noise not only varies at different features, but also has strong directionality. In this paper, we incorporate the directional uncertainty model into a quasiconvex optimization framework, in which global minimum of meaningful errors can be efficiently achieved, and accurate geometric reconstructions can be obtained from feature points that contain high directional uncertainty.

Models in Software Engineering

Abstract: In model-driven engineering, domain-specific languages (DSLs) play an important role in providing well-defined environments for modeling different aspects of a system. Detailed knowledge of the application domain as well as expertise in language engineering is required to create new languages. This research work proposes automated knowledge acquisition to support language engineers in early language development phases. We describe an iterative approach in which DSL development benefits from formalized knowledge sources and information extraction from text supporting domain analysis and metamodel construction. We show how the acquired knowledge is used to guide language engineers and how knowledge acquisition is adapted according to modeling decisions.

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.