A novel global methodology to analyze the embeddability of real-time image processing algorithms

Saussard, Romain; Bouzid, Boubker; Vasiliu, Marius; Reynaud, Roger

doi:10.1007/s11554-017-0686-3

Cited by 6 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many scholars have conducted in-depth research and discussion on this process in recent years. For example, Saussard, et al (2018) have scientifically described the current status of driver assistance systems, and they have proposed a feasible solution to combine image processing algorithms with the system and enable it to run in real environments. They revealed relevant implementation problems and specific implementation steps that have been solved by this scheme.…”

Section: Related Workmentioning

confidence: 99%

Algorithm-Oriented SIMD Computer Mathematical Model and Its Application

Jiang

2022

International Journal of Information and Communication Technology Education

View full text Add to dashboard Cite

This paper has designed a professional and practical SIMD computer mathematical model based on the SIMD physical machine model combined with the variable addition method. Furthermore, the model is applied in image collection, processing, and display operations, and a SIMD data parallel image processing system is finally established by absorbing the parallel computing advantages of the mathematical model. In addition, the data-parallel image processing algorithm is introduced and the convolutional neural network algorithm is optimized to promote the significant improvement of the main performance such as the accuracy of the application system. The final experimental results have shown that the highest accuracy of the data-parallel image processing algorithm reaches 93.3% and the lowest error rate reaches 0.11%, which proves the superiority of the SIMD computer mathematical model in image processing applications.

show abstract

Section: Related Workmentioning

confidence: 99%

Algorithm-Oriented SIMD Computer Mathematical Model and Its Application

Jiang

2022

International Journal of Information and Communication Technology Education

View full text Add to dashboard Cite

show abstract

“…As an important branch of the urban intelligent rail traffic signal control system, the traffic signal control system not only ensures the orderly progress of road traffic but also ensures the safe passage of pedestrians and vehicles. When there are few or no vehicles passing through, the pedestrian waiting time is too long, which is a waste of road resources 10 . The intelligent rail traffic signal control system solves the increasingly serious traffic problems.…”

Section: Vehicle Target Detection and Recognition Algorithm Based On ...mentioning

confidence: 99%

(Retracted) Intelligent rail transit signal control system based on image processing technology

Huang

2022

J. Electron. Imag.

View full text Add to dashboard Cite

.With the rapid development of the intelligent rail field, the intelligent rail traffic signal control system plays an increasingly important role, bringing greater convenience to people’s travel. Under normal circumstances, the trains are dispatched strictly according to the schedule, but in the daily operation of urban rail transit, the service is inevitably affected by many unpredictable uncertain factors. To ensure the safety of vehicles and smooth traffic, we proposed an intelligent rail traffic signal control system based on image processing technology. When the system detects that there are too many people waiting, it automatically adjusts the display time of the signal lights in real time according to the image, thus ensuring more time for passengers to get on the train, so as to realize the intelligent control of the track. The experimental results of our paper show that the accuracy of the improved vehicle target detection and recognition algorithm is more than 90%, which is higher than that of the algorithm without the improvement. Applying the proposed algorithm to image processing improved the recognition rate and accuracy. Through the test of the intelligent rail traffic signal control system based on image processing, it was found that the system effectively identified the number of people waiting in the lane and automatically adjusted the train closing time. The time required was only 1 s, and the responsiveness reached 99% to ensure the safety of vehicles and smooth traffic.

show abstract

“…The article ''A novel global methodology to analyze the embeddability of real-time image processing algorithms'' by Saussard et al [15] evaluates several heterogenous SoCs for ADAS and proposes three different mapping methods for applications with real-time constraints. Here, parallel applications are modeled in the form of a processing graph and performance models allow for pruning the vast search space of possible mappings to such parallel architectures.…”

Section: Heterogeneous Real-time Image Processingmentioning

confidence: 99%