Luc Van Gool

Bio: Luc Van Gool is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 133, co-authored 1307 publications receiving 107743 citations. Previous affiliations of Luc Van Gool include Microsoft & ETH Zurich.

Video Registration to SfM Models

Abstract: Registering image data to Structure from Motion (SfM) point clouds is widely used to find precise camera location and orientation with respect to a world model. In case of videos one constraint has previously been unexploited: temporal smoothness. Without temporal smoothness the magnitude of the pose error in each frame of a video will often dominate the magnitude of frame-to-frame pose change. This hinders application of methods requiring stable poses estimates (e.g. tracking, augmented reality). We incorporate temporal constraints into the image-based registration setting and solve the problem by pose regularization with model fitting and smoothing methods. This leads to accurate, gap-free and smooth poses for all frames. We evaluate different methods on challenging synthetic and real street-view SfM data for varying scenarios of motion speed, outlier contamination, pose estimation failures and 2D-3D correspondence noise. For all test cases a 2 to 60-fold reduction in root mean squared (RMS) positional error is observed, depending on pose estimation difficulty. For varying scenarios, different methods perform best. We give guidance which methods should be preferred depending on circumstances and requirements.

3D Structure from Images — SMILE 2000

Abstract: This paper presents techniques and animations developed from 1991 to 2000 that use digital photographs of the real world to create 3D models, virtual camera moves, and realistic computer animations. In these projects, images are used to determine the structure, appearance, and lighting conditions of the scenes. Early work in recovering geometry (and generating novel views) from silhouettes and stereo correspondence are presented, which motivate Façade, an interactive photogrammetric modeling system that uses geometric primitives to model the scene. Subsequent work has been done to recover lighting and reflectance properties of real scenes, to illuminate synthetic objects with light captured from the real world, and to directly capture reflectance fields of real-world objects and people. The projects presented include The Chevette Project (1991), Immersion 94 (1994), Rouen Revisited (1996), The Campanile Movie (1997), Rendering with Natural Light (1998), Fiat Lux (1999), and the Light Stage (2000).

Multi-view tracking of multiple targets with dynamic cameras

Abstract: We propose a new tracking-by-detection algorithm for multiple targets from multiple dynamic, unlocalized and unconstrained cameras. In the past tracking has either been done with multiple static cameras, or single and stereo dynamic cameras. We register several moving cameras using a given 3D model from Structure from Motion (SfM), and initialize the tracking given the registration. The camera uncertainty estimate can be efficiently incorporated into a flow-network formulation for tracking. As this is a novel task in the tracking domain, we evaluate our method on a new challenging dataset for tracking with multiple moving cameras and show that our tracking method can effectively deal with independently moving cameras and camera registration noise.

Visual modelling : from images to images

Abstract: This paper contains two parts. In the first part an automatic processing pipeline is presented that analyses an image sequence and automatically extracts camera motion, calibration and scene geometry. The system combines state-of-the-art algorithms developed in computer vision, computer graphics and photogrammetry. The approach consists of two stages. Salient features are extracted and tracked throughout the sequence to compute the camera motion and calibration and the 3D structure of the observed features. Then a dense estimate of the surface geometry of the observed scene is computed using stereo matching. The second part of the paper discusses how this information can be used for visualization. Traditionally, a textured 3D model is constructed from the computed information and used to render new images. Alternatively, it is also possible to avoid the need for an explicit 3D model and to obtain new views directly by combining the appropriate pixels from recorded views. It is interesting to note that even when there is an ambiguity on the reconstructed geometry, correct new images can often still be generated. Copyright © 2002 John Wiley & Sons, Ltd.

Vision Based Intelligent Wheel Chair Control: The Role of Vision and Inertial Sensing in Topological Navigation

Abstract: This paper describes ongoing research on vision based mobile robot navigation for wheel chairs. After a guided tour through a natural environment while taking images at regular time intervals, natural landmarks are extracted to automatically build a topological map. Later on this map can be used for place recognition and navigation. We use visual servoing on the landmarks to steer the robot. In this paper, we investigate ways to improve the performance by incorporating inertial sensors. © 2004 Wiley Periodicals, Inc.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

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.