Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
According to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveill...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/10/11/148 |
| _version_ | 1797510701090078720 |
|---|---|
| author | Sergio Robles-Serrano German Sanchez-Torres John Branch-Bedoya |
| author_facet | Sergio Robles-Serrano German Sanchez-Torres John Branch-Bedoya |
| author_sort | Sergio Robles-Serrano |
| collection | DOAJ |
| description | According to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveillance and intelligent traffic systems, an automated traffic accident detection approach becomes desirable for computer vision researchers. Nowadays, Deep Learning (DL)-based approaches have shown high performance in computer vision tasks that involve a complex features relationship. Therefore, this work develops an automated DL-based method capable of detecting traffic accidents on video. The proposed method assumes that traffic accident events are described by visual features occurring through a temporal way. Therefore, a visual features extraction phase, followed by a temporary pattern identification, compose the model architecture. The visual and temporal features are learned in the training phase through convolution and recurrent layers using built-from-scratch and public datasets. An accuracy of 98% is achieved in the detection of accidents in public traffic accident datasets, showing a high capacity in detection independent of the road structure. |
| first_indexed | 2024-03-10T05:35:06Z |
| format | Article |
| id | doaj.art-198e70c8d1cc42e7880cc1c02bba8bb8 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T05:35:06Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-198e70c8d1cc42e7880cc1c02bba8bb82023-11-22T22:57:02ZengMDPI AGComputers2073-431X2021-11-01101114810.3390/computers10110148Automatic Detection of Traffic Accidents from Video Using Deep Learning TechniquesSergio Robles-Serrano0German Sanchez-Torres1John Branch-Bedoya2Facultad de Minas, Universidad Nacional de Colombia, Sede Medellín 050041, ColombiaFacultad de Ingeniería, Universidad del Magdalena, Santa Marta 470001, ColombiaFacultad de Minas, Universidad Nacional de Colombia, Sede Medellín 050041, ColombiaAccording to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveillance and intelligent traffic systems, an automated traffic accident detection approach becomes desirable for computer vision researchers. Nowadays, Deep Learning (DL)-based approaches have shown high performance in computer vision tasks that involve a complex features relationship. Therefore, this work develops an automated DL-based method capable of detecting traffic accidents on video. The proposed method assumes that traffic accident events are described by visual features occurring through a temporal way. Therefore, a visual features extraction phase, followed by a temporary pattern identification, compose the model architecture. The visual and temporal features are learned in the training phase through convolution and recurrent layers using built-from-scratch and public datasets. An accuracy of 98% is achieved in the detection of accidents in public traffic accident datasets, showing a high capacity in detection independent of the road structure.https://www.mdpi.com/2073-431X/10/11/148urban traffic accidentdeep learningaccident detectionrecurrent neural networksconvolutional neural networks |
| spellingShingle | Sergio Robles-Serrano German Sanchez-Torres John Branch-Bedoya Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques Computers urban traffic accident deep learning accident detection recurrent neural networks convolutional neural networks |
| title | Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques |
| title_full | Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques |
| title_fullStr | Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques |
| title_full_unstemmed | Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques |
| title_short | Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques |
| title_sort | automatic detection of traffic accidents from video using deep learning techniques |
| topic | urban traffic accident deep learning accident detection recurrent neural networks convolutional neural networks |
| url | https://www.mdpi.com/2073-431X/10/11/148 |
| work_keys_str_mv | AT sergioroblesserrano automaticdetectionoftrafficaccidentsfromvideousingdeeplearningtechniques AT germansancheztorres automaticdetectionoftrafficaccidentsfromvideousingdeeplearningtechniques AT johnbranchbedoya automaticdetectionoftrafficaccidentsfromvideousingdeeplearningtechniques |