One of the most important data sources in Intelligent Transportation Systems is images source. Fixed cameras or portable ones can capture these images but the latter is more effective. In , a drone was used for freeway monitoring system. Cao et al.  proposed a system for vehicle detection and tracking using Unmanned Aerial Vehicles (UAVs). Also in , the similar system has been developed to monitor road conditions. Since, UAV images are captured in different situations and from different angles, so the powerful image processes and machine learning algorithms should be combined to extract accurate results. In this research, we consider the accident images and developed a deep learning method for feature extraction together with a mixture of experts for classification. For the first task, the outputs of the last max-pooling layer of a Convolution Neural Network (CNN) are used to extract the hidden features automatically. For the second task, a mixture of advanced variations of Extreme Learning Machine (ELM), is developed. This ensemble classifier combines the advantages of different ELMs by using a gating network and its accuracy is very high while the processing time is close to real-time. To show the efficiency, the different combinations of the traditional feature extraction and feature selection methods and the various classifiers are examined on two kinds of benchmarks including accident images dataset and some general datasets. It is shown that the proposed system detects the accidents with 99.31% precision, recall and F-measure. Besides, the precision of accident severity classification and involved-vehicles classification are 90.27% and 92.73%, respectively. This system is suitable for on-line processing on the accident images that will be captured by Unmanned Aerial Vehicles (UAV) or other surveillance systems. To see details, please refer to this reference:
- Convolution Neural Network Joint with Mixture of Extreme Learning Machines for Feature Extraction and Classification of Accident Images, Ali Pashaei, Mehdi Ghatee, Hedieh Sajedi, Journal of Real-time Image Processing, 17, pages 1051–1066 (2020).
Some Related References for more researches:
 B. Coifman, M. McCord, R. Mishalani, M. Iswalt and Y. and Ji, “ Roadway Traffic Monitoring from an Unmanned Aerial Vehicle,” IEE Proceedings-Intelligent Transport Systems, 2006.
 X. Cao, J. Lan, P. Yan and X. Li, “’Vehicle Detection and Tracking in Airborne Videos by Multi-Motion Layer Analysis’,” Machine Vision and Applications, vol. 23, no. 5, pp. 921-935, 2012.
N. Kim and M. Chervonenkis, “Situation Control of Unmanned Aerial Vehicles for Road Traffic Monitoring,” Modern Applied Science, vol. 9, no. 5, p. 1, 2015 .