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.

System identification of small-size unmanned helicopter dynamics

Abstract: Abstmcf: Flight testing of a fully-instrumented model-scale unmanned helicopter (Yamaha R-SO with loft. diameter rotor) was conducted for the purpose of dynamic model identification. This paper describes the application of CIFER' system identification techniques, which have been developed for full size helicopters, to this aircraft. An accurate, high-bandwidth, linear state-space model was derived for the hover condition. The model structure includes the explicit representation of regressive rotor-flap dynamics, rigid-body fuselage dynamics, and the yaw damper. The R-50 codiguration and identified dynamics are compared with those of a dynamically scaled UH-1H. The identified model shows excellent predictive capability and is well suited for flight control design and simulation applications.

Robust full-motion recovery of head by dynamic templates and re-registration techniques

Abstract: This paper presents a method to recover the full-motion (3 rotations and 3 translations) of the head from an input video using a cylindrical head model. Given an initial reference template of the head image and the corresponding head pose, the head model is created and full head motion is recovered automatically. The robustness of the approach is achieved by a combination of three techniques. First, we use the iteratively re-weighted least squares (IRLS) technique in conjunction with the image gradient to accommodate non-rigid motion and occlusion. Second, while tracking, the templates are dynamically updated to diminish the effects of self-occlusion and gradual lighting changes and to maintain accurate tracking even when the face moves out of view of the camera. Third, to minimize error accumulation inherent in the use of dynamic templates, we re-register images to a reference template whenever head pose is close to that in the template. The performance of the method, which runs in real time, was evaluated in three separate experiments using image sequences (both synthetic and real) for which ground truth head motion was known. The real sequences included pitch and yaw as large as 40° and 75°, respectively. The average recovery accuracy of the 3D rotations was about 3°. In a further test, the method was used as part of a facial expression analysis system intended for use with spontaneous facial behavior in which moderate head motion is common. Image data consisted of 1-minute of video from each of 10 subjects while engaged in a 2-person interview. The method successfully stabilized face and eye images allowing for 98% accuracy in automatic blink recognition.

DigitEyes: vision-based hand tracking for human-computer interaction

Abstract: Computer sensing of hand and limb motion is an important problem for applications in human-computer interaction (HCI), virtual reality, and athletic performance measurement. Commercially available sensors are invasive, and require the user to wear gloves or targets. We have developed a noninvasive vision-based hand tracking system, called DigitEyes. Employing a kinematic hand model, the DigitEyes system has demonstrated tracking performance at speeds of up to 10 Hz, using line and point features extracted from gray scale images of unadorned, unmarked hands. We describe an application of our sensor to a 3D mouse user-interface problem. >

Video OCR: indexing digital new libraries by recognition of superimposed captions

Abstract: The automatic extraction and recognition of news captions and annotations can be of great help locating topics of interest in digital news video libraries. To achieve this goal, we present a technique, called Video OCR (Optical Character Reader), which detects, extracts, and reads text areas in digital video data. In this paper, we address problems, describe the method by which Video OCR operates, and suggest applications for its use in digital news archives. To solve two problems of character recognition for videos, low-resolution characters and extremely complex backgrounds, we apply an interpolation filter, multiframe integration and character extraction filters. Character segmentation is performed by a recognition-based segmentation method, and intermediate character recognition results are used to improve the segmentation. We also include a method for locating text areas using text-like properties and the use of a language-based postprocessing technique to increase word recognition rates. The overall recognition results are satisfactory for use in news indexing. Performing Video OCR on news video and combining its results with other video understanding techniques will improve the overall understanding of the news video content.

Tracking in unstructured crowded scenes

Abstract: This paper presents a target tracking framework for unstructured crowded scenes. Unstructured crowded scenes are defined as those scenes where the motion of a crowd appears to be random with different participants moving in different directions over time. This means each spatial location in such scenes supports more than one, or multi-modal, crowd behavior. The case of tracking in structured crowded scenes, where the crowd moves coherently in a common direction, and the direction of motion does not vary over time, was previously handled in [1]. In this work, we propose to model various crowd behavior (or motion) modalities at different locations of the scene by employing Correlated Topic Model (CTM) of [16]. In our construction, words correspond to low level quantized motion features and topics correspond to crowd behaviors. It is then assumed that motion at each location in an unstructured crowd scene is generated by a set of behavior proportions, where behaviors represent distributions over low-level motion features. This way any one location in the scene may support multiple crowd behavior modalities and can be used as prior information for tracking. Our approach enables us to model a diverse set of unstructured crowd domains, which range from cluttered time-lapse microscopy videos of cell populations in vitro, to footage of crowded sporting events.

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.