Lehrstuhl für Allgemeine Elektrotechnik und Theoretische Nachrichtentechnik
Prof. Dr.- Ing. Anton Kummert
Dr.-Ing. Jörg Velten
|Telefon:||+49 (0)202 439 1811|
Tomographical object detection using a reduced number of projection angles
of the 8th International Workshop on Multidimensional (nD) Systems (nDS'13) , Seite 181 - 186.
Feature Recycling Cascaded SVM Classifier Based on Feature Selection of HOGs for Pedestrian Detection
in 6th International Conference on Multimedia Communications, Services and Security ( MCSS'13) , Seite 82 - 94.
People Detection and Tracking from a Top-View Position Using a Time-of-Flight Camera
in 6th International Conference on Multimedia Communications, Services and Security (MCSS'13) , Seite 213 - 223.
Sensor system blockage detection for night time headlight control based on camera and radar sensor information
of the 15th International IEEE Conference on Intelligent Transportation Systems (ITSC'12) , Seite 78 - 83.
Schlüsselwörter: Head light detection, Radar and camera sensor fusion, Sensor data fusion
Zusammenfassung: Driver assistance systems support overstrained and affected drivers and become more and more essential for series-production vehicles. In this paper a procedure for detection of a misaligned or blocked sensor system, including a radar and a camera sensor, will be introduced. It is important to inform the driver if an automatic headlight control is working reliable, in other words without limitations caused by external influence (e.g. dirt on the windscreen). The blockage detection algorithm is based on the fusion result of electronic radar measurements and a vision based head- and taillight detection algorithm. Results of the blockage detection algorithm are evaluated on misaligned measurements and online in a vehicle test system.
Tomographical scene reconstruction in the active safety car project
of the 15th International IEEE Conference on Intelligent Transportation Systems (ITSC'12) , Seite 307 -312.
Schlüsselwörter: active safety car project, automobiles, Biomedical imaging, camera based measurements, cameras, driver assistance systems, driver information systems, driveway monitoring, Image reconstruction, radiographing, road safety, Signal processing algorithms, tomographical background information, tomographical scene reconstruction algorithm, Tomography, Vehicles, view camera, visual light rays, Visualization
Realization of multidimensional signal processing systems given in natural k-D state space descriptionMultidimensional Systems and Signal Processing, 23(1-2):281 - 290
Method and device for producing image information
Zusammenfassung: The invention relates to a method for generating image information of an image of an image sequence using the image information of a first image. The object of providing a method for generating image information of an image of an image sequence so that a stroboscopic effect is avoided even in the case of varyingly fast movements of the image information and so that a clear display is still possible in the case of low speeds of the image information, is achieved in that the number of intermediate images is determined as a function of the value of the first movement measure and a weighting factor is calculated for each intermediate image.
Multisensor data fusion for advanced driver assistance systems - the Active Safety Car project
of the 7th International Workshop on Multidimensional (nD) Systems (nDS'11) , Seite 1 - 5.
Schlüsselwörter: active safety car project, automobiles, driver assistance systems, image processing, image segmentation, multisensor data fusion, object detection, object segmentation, sensor fusion, series production vehicles, traffic engineering computing
Zusammenfassung: Driver assistance systems support overstrained and affected drivers and become more and more essential for series-production vehicles. Object detection and segmentation is one of the most challenging research topics in this field. In order to warn the driver or automatically break before a potential collision, objects intersecting the path of the host vehicle have to be detected and classified. Most recently developed approaches are based on two dimensional image processing, sometimes in combination with a tracking algorithm associating detections in consecutive frames to one and the same object. Further robustness is achieved by multisensor data fusion, i.e. information by two or more different sensors (e.g. camera and radar data) are fused in order to get a much more reliable result. Another aspect for safety applications is communication between cars, which provides additional sensor locations and thus also requires data fusion technology. Two different approaches for data fusion are proposed and first results are presented.
On multidimensional velocity filter banks for video-based motion analysis of world-coordinate objects
of the 7th International Workshop on Multidimensional (nD) Systems (nDS'11) , Seite 1 - 5.
Schlüsselwörter: channel bank filters, image motion analysis, image sequences, inverse perspective mapping, linear multidimensional filter theory, multidimensional velocity filter banks, parameterized filter bank, time invariant transfer function, video based motion analysis, video signal processing, world coordinate objects
Zusammenfassung: Linear multidimensional filter theory provides an elegant way to analyse movement within image sequences, i.e. to separate objects moving in different directions or at different speeds. Due to its time-invariant transfer function a single filter is restricted to specific motions, for which reason a consecutively parameterized filter bank is needed to differentiate a broader set of movement. In this paper, an introduction to velocity filtering is given and unwanted side-effects are discussed, i.e. spatio-temporal ringing and perspective distortion. As a practical example a traffic scene is analysed by means of inverse perspective mapping followed by a velocity filter bank.
Fighting the wagon-wheel effect - A new anti-aliasing method for video signal generation
of the IEEE 10th International Conference on Signal Processing (ICSP'10) , Seite 936 - 939.
Schlüsselwörter: 1D filter, 1D signal processing, antialiasing, antialiasing method, eye, human eye, image sampling, image sequence, image sequences, sampling theorem, video signal generation, video signal processing, visual perception, wagon-wheel effect
Zusammenfassung: In this paper a new method of avoiding aliasing effects in synthetically generated video is presented. In other words, aim is to remove aliasing effects that disturb visual perception of the synthetically generated image sequence by the human eye. In general, aliasing occurs if the widely known sampling theorem is not met. In the field of video applications, more often than not the limiting factor leading to these disturbing effects is the temporal sampling rate (a.k.a. "frame rate"). The standard approach known from 1-D signal processing applications, i.e. increasing the sampling rate, is effective but very hardware-expensive as it introduces additional frames that have to be processed by the underlying system. In contrast, the proposed method uses a cheap 1-D filter in space-direction to achieve the same aliasing-free result.
Laser phase shift distance meter for vision based driver assistance systems
of the IEEE International Conference on Imaging Systems and Techniques (IST'10) , Seite 220 -224.
Schlüsselwörter: camera based systems, cameras, car-to-car-communication, computer vision, distance measurement, driver information systems, electronic data interchange, image information exchange, laser measurement system design, laser phase shift distance meter, laser ranging, measurement by laser beam, phase shift laser range finder, phase shifters, tomographic image processing, vision based driver assistance systems
Zusammenfassung: Camera based systems are gaining popularity in automotive driver assistance systems. They are used to detect obstacles, road signs, road markings and other road users. Today, even low cost camera technology enables obtaining a very good image resolution and therefore cameras are able to give a good 2-dimensional image. Due to the projection of an image into the camera's sensor plane, its main disadvantage is the difficulty to estimate the distance of objects projected onto the sensor plane. This difficulty can be overcome if image information is exchanged by several cars via car-to-car-communication. Thinkable solutions range from simply exchanging estimated positions of detected objects up to tomographic image processing. For these methods, knowledge of an exact position of the vehicles is crucial. Conventional positioning methods do not deliver the required accuracy. Therefore a phase shift laser distance measuring device is proposed that is used to measure the vehicles precise position relative to landmarks. Considering the special requirements resulting from this application, the new laser measurement system design is introduced. Measurement results demonstrate its applicability. Special attention is laid on error sources such as crosstalk in this new implementation of a phase shift laser range finder.
A new anti-aliasing approach for improved motion-based object detection using linear filters
of the IEEE Intelligent Vehicles Symposium (IV'10) , Seite 915 - 920.
San Diego, California, USA
Schlüsselwörter: antialiasing, antialiasing approach, blind spot warning systems, camera signal, cameras, computational power, driver assistance systems, driver information systems, improved motion based object detection, linear filter, linear shift invariant, low temporal resolution, object detection
Zusammenfassung: In this paper a new anti-aliasing approach for motion-based object detection using linear shift invariant (LSI) filters is presented. Mainly originating from the field of signal processing, LSI-filter-based motion detection has been topic of research for a long time, though due to low computational power of contemporary computers the developed systems have been unfeasible for application in mass products like driver assistance systems. However, recent progress in hardware in conjunction with decreasing costs makes using linear filters a very interesting alternative of increasing performance of common approaches. One of the most important factors falsifying object detection results obtained using linear shift invariant (LSI) is aliasing. This is mostly caused by the low temporal resolution of the camera signal which leads to the fact that the sampling theorem does not hold for objects moving at high speed in the image plane. In general, aliasing errors cannot be removed after sampling. Under certain conditions, however, their impact on the filter result can be successfully decreased using the approach presented in this paper. The applicability of the new approach is demonstrated using scenes recorded by a camera installed in a blind spot warning system.