Search

In this work we present a novel system for autonomous mobile robot navigation. With only an omnidirectional camera as sensor, this system is able to build automatically and robust accurate topologically organised environment maps of a complex, natural environment. It can localise itself using that map at each moment, including both at startup (kidnapped robot) or using knowledge of former localisations. The topological nature of the map is similar to the intuitive maps humans use, is memory-efficient and enables fast and simple path planning towards a specified goal. We developed a real-time visual servoing technique to steer the system along the computed path. The key technology making this all possible is the novel fast wide baseline feature matching, which yields an efficient description of the scene, with a focus on man-made environments.

This work presents a unique system for autonomous mobile robot navigation. The main sensor is an omnidirectional camera. The proposed system is capable to build automatically a topological map complex, natural environments. It can localise itself using that map on each moment, after startup (kidnapped robot) or using knowledge of former localisations. The topological nature of the map enables fast and simple path planning towards a specified goal. A visual servoing technique is implemented to steer the system along the computed path. The key technology making this all possible is the novel fast wide baseline feature matching, which yields an efficient abstraction of the wealth of information offered by the visual sensor. Goedemé T., Nuttin M., Tuytelaars T., Van Gool L., ''Omnidirectional vision based topological navigation'', 15th international symposium on measurement and control in robotics - ISMCR 2005, November 8-10, 2005, Brussels, Belgium. ispartof: Proceedings 15th international symposium on measurement and control in robotics - ISMCR 2005 ispartof: International symposium on measurement and control in robotics - ISMCR 2005 location:Brussels, Belgium date:8 Nov - 10 Nov 2005 status: published

In this paper we present a technique to linearly recover 2D structure and motion in man made environments from three uncalibrated omnidirectional views. We use vertical lines from the scene which are projected as radial lines in the images and are automatically matched. The algorithm is based on a 1D radial trifocal tensor which encodes the relations of the three views and the projected lines. We include experiments with real images, which demonstrate the good performance of the method and its application to robotic tasks, such as robot localization based in a database of reference images or to obtain the initial values of robot and landmarks localization in SLAM algorithms. Sagüés C., Murillo A.C., Guerrero J.J., Goedemé T., Tuytelaars T., Van Gool L., ''Localization with omnidirectional images using the radial trifocal tensor'', Proceedings IEEE international conference on robotics and automation - ICRA 2006, pp. 551-556, May 15-19, 2006, Orlando, Florida, USA. ispartof: pages:551-556 ispartof: Proceedings IEEE international conference on robotics and automation - ICRA 2006 vol:2006 pages:551-556 ispartof: IEEE international conference on robotics and automation - ICRA 2006 location:Orlando, Florida, USA date:15 May - 19 May 2006 status: published

Upcoming fast vision techniques for finding image correspondences enable reliable real-time visual homing, i.e. the guidance of a mobile robot from a arbitrary start pose towards a goal pose defined by an image taken there. Two approaches emerge in the field that differ in the fact that the structure of the scene is estimated or not. In this paper, we compare these two approaches for the general case and especially for our application, being automatic wheelchair navigation. Goedemé T., Vanhooydonck D., Demeester E., Nuttin M., Tuytelaars T., Van Gool L., ''Is structure needed for omnidirectional visual homing ?'', 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation - CIRA 2005, June 27-30, 2005, Espoo, Finland. ispartof: pages:303-308 ispartof: Proceedings 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation - CIRA 2005 pages:303-308 ispartof: IEEE International Symposium on Computational Intelligence in Robotics and Automation - CIRA 2005 location:Espoo, Finland date:27 Jun - 30 Jun 2005 status: published

Goedemé T., Nuttin M., Tuytelaars T., Van Gool L., ''Vision based intelligent wheel chair control: the role of vision and inertial sensing in topological navigation'', Workshop on integration of vision and inertial sensors, INERVIS-2003, pp. 1883-1890, June 29, 2003, Coimbra, Portugal. ispartof: pages:1883-1890 ispartof: Proceedings workshop on integration of vision and inertial sensors, INERVIS-2003 pages:1883-1890 ispartof: Workshop on integration of vision and inertial sensors, INERVIS-2003 location:Coimbra, Portugal date:29 Jun - 29 Jun 2003 status: published

Combining new, low-cost thermal infrared and time-of-flight range sensors provides new opportunities. In this position paper we explore the possibilities of combining these sensors and using their fused data for person detection. The proposed calibration approach for this sensor combination differs from the traditional stereo camera calibration in two fundamental ways. A first distinction is that the spectral sensitivity of the two sensors differs significantly. In fact, there is no sensitivity range overlap at all. A second distinction is that their resolution is typically very low, which requires special attention. We assume a situation in which the sensors' relative position is known, but their orientation is unknown. In addition, some of the typical measurement errors are discussed, and methods to compensate for them are proposed. We discuss how the fused data could allow increased accuracy and robustness without the need for complex algorithms requiring large amounts of computational power and training data., Comment: Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics

In this paper we present a novel method for the automatic analysis of mobile eye-tracking data in natural environments. Mobile eye-trackers generate large amounts of data, making manual analysis very time-consuming. Available solutions, such as marker-based analysis minimize the manual labour but require experimental control, making real-life experiments practically unfeasible. We present a novel method for processing this mobile eye-tracking data by applying object, face and person detection algorithms. Furthermore we present a temporal smoothing technique to improve the detection rate and we trained a new detection model for occluded person and face detections. This enables the analysis to be performed on the object level rather than the traditionally used coordinate level. We present speed and accuracy results of our novel detection scheme on challenging, large-scale real-life experiments. De Beugher S., Brône G., Goedemé T., ''Automatic analysis of in-the-wild mobile eye-tracking experiments using object, face and person detection'', 9th international conference on computer vision theory and applications - VISAPP 2014, pp. 625-633, January 5-8, 2014, Lisbon, Portugal. no issn ispartof: pages:625-633 ispartof: Proceedings of the 9th International Conference on Computer Vision Theory and Applications - (Volume 1) vol:1 pages:625-633 ispartof: VISRAPP 2014: International Conference on Computer Vision Theory and Applications location:Lisbon, Portugal date:5 Jan - 8 Jan 2014 status: published

A new and fast way to find local image correspondences for wide baseline image matching is described. The targeted application is visual navigation, e.g. of a semi-automatic wheelchair. Such applications pose some additional requirements, like the need to work with natural landmarks rather than artificial markers, and the need to recognize locations fast. The restricted motion of the camera can be exploited to simplify the feature extraction. These features should support their identification from different, but nevertheless restricted viewing directions, and under variable illumination conditions. The paper proposes a specialization of so-called affine invariant regions for these particular conditions, which in this case simplifies to column segments. Their applicability is wider than robot navigation, and includes localization for wearable computing and scene recognition for automatic movie indexing. Goedemé T., Tuytelaars T., Van Gool L., ''Fast wide baseline matching for visual navigation'', Proceedings IEEE computer society conference on computer vision and pattern recognition - CVPR2004, vol. I, pp. 24-29, June 27 - July 2, 2004, Washington, DC, USA. ispartof: pages:24-29 ispartof: Proceedings IEEE computer society conference on computer vision and pattern recognition - CVPR2004 vol:1 pages:24-29 ispartof: IEEE computer society conference on computer vision and pattern recognition - CVPR2004 location:Washington, DC, USA date:27 Jun - 2 Jul 2004 status: published

This paper focuses on a thorough comparison of the two main hardware targets for real-time optimization of a computer vision algorithm: GPU and FPGA. Based on a complex case study algorithm for threaded isle detection, implementation on both hardware targets is compared in terms of resulting time performance, code translation effort, hardware cost, power efficiency and integrateability. A real-life case study as described in this paper is a very useful addition to discussions on a more theoretical level, going beyond artificial experiments. In our experiments, we show the speed-up gained by porting our algorithm to FPGA using manually written VHDL and to a heterogeneous GPU/CPU architecture with the OpenCL language. Also, issues and problems occurring during the code porting are detailed. Struyf L., De Beugher S., Van Uytsel D.H., Kanters F., Goedemé T., ''The battle of the giants: a case study of GPU vs FPGA optimisation for real-time image processing'', Proceedings 4th international conference on pervasive and embedded computing and communication systems – PECCS 2014, vol. 1, pp. 112-119, January 7-9, 2014, Lisbon, Portugal. ispartof: pages:112-119 ispartof: Proceedings PECCS 2014 vol:1 pages:112-119 ispartof: International conference on pervasive and embedded computing and communication systems – PECCS 2014 location:Lisbon, Portugal date:7 Jan - 9 Jan 2014 status: published

In this paper we present a multi-pedestrian detection and tracking framework targeting a specific application: detecting vulnerable road users in a truck's blind spot zone. Research indicates that existing non-vision based safety solutions are not able to handle this problem completely. Therefore we aim to develop an active safety system which warns the truck driver if pedestrians are present in the truck's blind spot zone. Our system solely uses the vision input from the truck's blind spot camera to detect pedestrians. This is not a trivial task, since the application inherently requires real-time operation while at the same time attaining very high accuracy. Furthermore we need to cope with the large lens distortion and the extreme viewpoints introduced by the blind spot camera. To achieve this, we propose a fast and efficient pedestrian detection and tracking framework based on our novel perspective warping window approach. To evaluate our algorithm we recorded several realistically simulated blind spot scenarios with a genuine blind spot camera mounted on a real truck. We show that our algorithm achieves excellent accuracy results at real-time performance, using a single core CPU implementation only. ispartof: pages:412-420 ispartof: Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods pages:412-420 ispartof: International Conference on Pattern Recognition Applications and Methods location:Angers, France date:6 Mar - 8 Mar 2014 status: published

In this paper, we present a real-time pedestrian tracker that combines a robust appearance-based pedestrian detector with application-specific constraints and motion information. The targeted application is the automatic detection of vulnerable road users in blind spot cameras on trucks. This application imposes several challenges that need to be tackled. Vulnerable road users are a very diverse class, and we need a high precision and recall rate with real-time performance. Here, we present a first step towards such an automatic detection system. The novelty of our approach is the extension of a robust pedestrian detector towards real-time performance. The information from the appearance-based detector is used in combination with motion-based estimations to efficiently reduce the search space for the appearance-based detector in consecutive frames. This results in a multi-pedestrian tracker from a moving camera which is both optimized in terms of accuracy and speed. We recorded several data sequences to evaluate our pedestrian tracker, and performed initial experiments with promising results. Van Beeck K., Goedemé T., Tuytelaars T., ''Towards an automatic blind spot camera: robust real-time pedestrian tracking from a moving camera'', Proceedings 12th IAPR conference on machine vision applications - MVA 2011, pp. 528-531, June 13-15, 2011, Nara, Japan. ispartof: pages:528-531 ispartof: Proceedings of the twelfth IAPR Conference on Machine Vision Applications pages:528-531 ispartof: IAPR Conference on Machine Vision Applications - MVA 2011 location:Nara, Japan date:13 Jun - 15 Jun 2011 status: published

In the last few decades there have been substantial improvements in approaches for solving the Boolean satisfiability problem. Many of these consisted in elaborating on existing algorithms, both on the side of complete solvers as in the area of incomplete solvers. Besides the improvements to existing solving methods, however, recent evolutions in SAT solving take the form of combining several solvers into one, resulting in parallel solvers and so-called hybrid solvers. Our goal is to combine both approaches, by presenting a parallel hybrid solver. The parallelism exists on two levels: we run a complete solver on the CPU concurrently with an incomplete solver on the GPU, where the latter in turn consists of a massively parallel local search algorithm. We implemented our approach using the OpenCL framework, and present preliminary experimental results. Beckers S., De Samblanx G., De Smedt F., Goedemé T., Struyf L., Vennekens J., ''Parallel hybrid SAT solving using OpenCL'', 24th Benelux conference on artificial intelligence - BNAIC-2012, pp. 11-18, October 25-26, 2012, Maastricht, The Netherlands. ispartof: pages:11-18 ispartof: Proceedings BNAIC 2012 pages:11-18 ispartof: Benelux Conference on Artificial Intelligence - BNAIC 2012 location:Maastricht, The Netherlands date:25 Oct - 26 Oct 2012 status: published

De Smedt F., Billiauws I., Goedemé T., ''Neural networks and low-cost optical filters for plant segmentation'', International journal of computer information systems and industrial management applications (IJCISIM), vol. 3, pp. 804-811, June 2011. ispartof: International Journal of Computer Information Systems and Industrial Management Applications vol:3 pages:804-811 status: published

Pedestrian detection is a topic in computer vision of great interest for many applications. Due to that, a large amount of pedestrian detection techniques are presented in current literature, each one improving previous techniques. The improvement in accuracy in recent pedestrian detection, is commonly in combination with a higher computational requirement. Although, recently a technique was proposed to combine multiple detection algorithms to improve accuracy instead. Since the evaluation speed of this combination is dependent on the detection algorithm it uses, we provide an open framework that includes multiple pedestrian detection algorithms, and the technique to combine them. We show that our open implementation is superior on speed, accuracy and peak memory-use when compared to other publicly available implementations. ispartof: pages:551-558 ispartof: Proceedings of the 10th International Conference on Computer Vision Theory and Applications - (Volume 2) (VISIGRAPP 2015) vol:2 pages:551-558 ispartof: VISAPP location:Berlin, Germany date:11 Mar - 13 Mar 2015 status: published

We propose a method for computing the absolute distances to obstacles using only one omnidirectional camera. The method is applied to mobile robots. We achieve this without restricting the application to predetermined translations or the use of artificial markers. In contrast to prior work, our method is able to build absolute scale 3D without the need of a known baseline length, traditionally acquired by an odometer. Instead we use the ground plane assumption together with the camera system’s height to determine the scale factor. Using only one omnidirectional camera our method is proven to be cheaper, more informative and more com- pact than the traditional methods for distance determination, especially when a robot is already equipped with a camera for e.g. navigation. An additional advantage is that it provides more information since it determines distances in a 3D space instead of one plane. The experiments show promising results. The algorithm is indeed capable of determining the distances in meters to features and obstacles and is able to locate all major obstacles in the scene. Millnert O., Goedemé T., Tuytelaars T., Van Gool L., Hüntemann A., Nuttin M., ''Range determination for mobile robots using one omnidirectional camera'', 3rd international conference on informatics in control, automation and robotics - ICINCO 2006, pp. 366-371, August 1-5, 2006, Setúbal, Portugal. ispartof: pages:366-371 ispartof: Proceedings 3rd international conference on informatics in control, automation and robotics - ICINCO 2006 vol:RA pages:366-371 ispartof: International conference on informatics in control, automation and robotics - ICINCO 2006 location:Setúbal, Portugal date:1 Aug - 5 Aug 2006 status: published