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.

Feature Localization Error in 3D Computer Vision

Abstract: Uncertainty modeling in 3D Computer Vision typically relies on propagating the uncertainty of measured feature positions through the modeling equations to obtain the uncertainty of the 3D shape being estimated. It is widely believed that this adequately captures the uncertainties of estimated geometric properties when there are no large errors due to mismatching. However, we identify another source of error which we call feature localization error. This captures how well a feature corresponds to the true 3D point, rather than how well features correspond over multiple images. We model this error as independent of the tracking error, and when combined as part of the total error, we show that it is significant and may even dominate the 3D reconstruction error.

Approximate representation of unknown objects with a single-line scanning lidar and a video camera

Abstract: Models are useful for many computer vision tasks, such as object detection, recognition, and tracking. Computer vision tasks must handle situations where unknown objects appear and must detect and track some object which is not in the trained database. In such cases, the system must learn or, otherwise derive, descriptions of new objects. In this dissertation, we investigate creating a representation of previously unknown objects that newly appear in the scene. The representation is to create a viewpoint-invariant and scale-normalized model approximately describing an unknown object. Those properties of the representation facilitate 3D tracking of the object using 2D-to-2D image matching. The representation has both benefits of an implicit model (referred to as a view-based model) and an explicit model (referred to as a shape-based model). The object representation is created using multi-modal sensors. We illustrate the benefits of the object representation with two applications: object detection and 3D tracking. We extend the object representation to an explicit model by imposing a shape prior and combining two existing approaches.

Uncertainty modeling for optimal structure from motion. Commentary

Abstract: The parameters estimated by Structure from Motion (SFM) contain inherent indeterminacies which we call gauge freedoms. Under a perspective camera, shape and motion parameters are only recovered up to an unknown similarity transformation. In this paper we investigate how covariance-based uncertainty can be represented under these gauge freedoms. Past work on uncertainty modeling has implicitly imposed gauge constraints on the solution before considering covariance estimation. Here we examine the effect of selecting a particular gauge on the uncertainty of parameters. We show potentially dramatic effects of gauge choice on parameter uncertainties. However the inherent geometric uncertainty remains the same irrespective of gauge choice. We derive a Geometric Equivalence Relationship with which covariances under different parametrizations and gauges can be compared, based on their true geometric uncertainty. We show that the uncertainty of gauge invariants exactly captures the geometric uncertainty of the solution, and hence provides useful measures for evaluating the uncertainty of the solution. Finally we propose a fast method for covariance estimation and show its correctness using the Geometric Equivalence Relationship.

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.