.png){kind=icon}
.png){kind=icon}
Return
Adaptive machine learning algorithm for human target detection in IoT environment
.png){kind=icon}
PRE
AI
DOI：10.1007/s00607-022-01123-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The emergence of Internet of things (IoT) technology has significantly influenced daily life and promoted the development of intelligent transportation systems and pilotless automobiles. In complex traffic environments such as curves and intersections, pilotless automobiles face some problems in pedestrian recognition, such as low detection distance accuracy and occlusion. To improve the timeliness of end-to-end information interaction and the early warning effect of anti-collision systems, a pedestrian target information fusion algorithm based on adaptive machine learning is proposed in the environment of Internet of vehicles (IoV). The pedestrian information acquired by roadside and on-board cameras is pretreated using a Kalman filter; then, the best position of the pedestrian target can be estimated and confirmed by integrating the time-space alignment, fuzzy association, and Kalman filtering results. Experiments show that both the maximum absolute error and the absolute mean error of the pedestrian trajectory are reduced significantly, i.e., by 45.0% and 58.5%, respectively, compared with those before trajectory fusion. Compared with S-LSTM and S-GAN methods, reasoning time is greatly reduced.Thus, the accuracy of pedestrian trajectory detection is improved by the fusion algorithm, and the warning accuracy of the system is enhanced.
Keywords:
Internet of vehicles
Machine learning
Kalman filter
Trajectory correlation
Information fusion