Early and Multi Level Fusion for Reliable Automotive Safety Systems

Scheunert, U.; Lindner, Philipp; Richter, Eric; Tatschke, T.; Schestauber, D.; Fuchs, Ernst; Wanielik, Gerd

doi:10.1109/ivs.2007.4290114

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the above three levels of multi-source information fusion, some methods have been proposed based on multi-level fusion, which enriches the framework of multi-source information fusion. Haberjahn et al [77] and Scheunert et al [78] proposed a multi-level multi-source information fusion structure that combines different levels of fusion information to finally gain a perception of the traffic scenarios.…”

Section: Hierarchical Fusion Structure Of Multiple Sensorsmentioning

confidence: 99%

“…The resulting feature maps are combined to obtain a significant visual feature map. The local entropy model [120], multi-scale quaternion Fourier transform [78], and other significant feature-based algorithms also effectively represent the visual attention model. Attention mechanism has a wide range of applications in deep learning.…”

Section: Selective Attention Mechanism Of Traffic Scene Perceptionmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous driving: cognitive construction and situation understanding

Chen

Jian

Huang

et al. 2019

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

Section: Hierarchical Fusion Structure Of Multiple Sensorsmentioning

confidence: 99%

Section: Selective Attention Mechanism Of Traffic Scene Perceptionmentioning

confidence: 99%

Autonomous driving: cognitive construction and situation understanding

Chen

Jian

Huang

et al. 2019

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The processing took place on different levels of abstraction [9], [10], [11]. In particular raw laser data from a 4 layer laser scanner was pre-processed on signal level and then forwarded to higher level processing structures.…”

Section: A Processing Overviewmentioning

confidence: 99%

3D LIDAR processing for vehicle safety and environment recognition

Lindner

Wanielik

2009

2009 IEEE Workshop on Computational Intelligence in Vehicles and Vehicular Systems

Self Cite

View full text Add to dashboard Cite

Automotive safety systems like "Adaptive Cruise Control" (ACC), "Lane Change Assist" and pre-crash systems are nowadays dealing with the detection of vehicles on the road. All major upper class vehicle manufacturers like Mercedes, BMW, Chrysler and Lexus as well as leading suppliers (Bosch, Continental, Delphi) are currently developing intelligent vehicle safety systems. For vehicle environment perception many different sensors are under investigation. Well known and cheap devices like grayscale cameras are already integrated in many cars today, e.g. for parking assist functions. To meet the requirements for extremely reliable and robust environment recognition additional sensors and multi sensor data fusion approaches have to be applied. New sensors like 3-dimensional measuring multilayer laser scanner systems will be introduced in the near future to deliver environment information for these systems. By fusing multiple sensors like laser and radar systems the reliability level of automotive safety applications will be improved significantly. The paper presents an approach for the processing of the data of a multilayer laser scanner (lidar) for the detection of vehicles in road environments. The lidar data is processed using a new 3-dimensional occupancy grid. An example is given for an automotive pre-crash safety application.

show abstract

“…The set of all false alarms can be represented by F P f def =¨p P P f V r2R f @ a2A f a = (r; p) © : (6) Furthermore, so-called classification errors can be determined as long as the perception system itself carries out the classification task. Let t 1 : R f 3 C and t 2 : P f 3 C respectively denote the classification type of an object, then the set of all wrong classified objects in frame f can be written as CE f def =¨p P P f W r2R f (p; r) P A f t 2 (p) T = t 1 (r) © : (7) Over a series of frames F the measures for false alarms (F P ), missed detections (M D), the detection rate (HIT ) and the classification error (CE) can be determined from these sets as follows:…”

Section: Calculation Of Performance Measuresmentioning

confidence: 99%

“…[7], [8]) can be generated automatically. Furthermore, it would be feasible to create an index of recordings from the reference information.…”

Section: Future Workmentioning

confidence: 99%

Semi-autonomous reference data generation for perception performance evaluation

Tatschke

Farber

Fuchs

et al. 2007

2007 10th International Conference on Information Fusion

Self Cite

View full text Add to dashboard Cite

Abstract-In the development phase of perception systems (e. g. for advanced driver assistance systems) general interest is pointing towards the performance of the respective detection and tracking algorithms. One common way to evaluate such systems relies on simulated data which is used as a reference. We present a semi-autonomous method, which allows the extraction of reference data from sensor recordings (including data at least from a camera and a distance measuring sensor device). Furthermore, we show how to combine these reference data with the output from the detection or fusion system and how to derive performance statistics of the system. As the generated reference information can be stored along with the sensor recordings, this method also facilitates the comparison of different software versions or algorithm parameters.

show abstract

Early and Multi Level Fusion for Reliable Automotive Safety Systems

Cited by 8 publications

References 12 publications

Autonomous driving: cognitive construction and situation understanding

Autonomous driving: cognitive construction and situation understanding

3D LIDAR processing for vehicle safety and environment recognition

Semi-autonomous reference data generation for perception performance evaluation

Contact Info

Product

Resources

About