A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology
One of the recent news headlines is that a pedestrian was killed by an autonomous vehicle because safety features in this vehicle did not detect an object on a road correctly. Due to this accident, some global automobile companies announced plans to postpone development of an autonomous vehicle. Fur...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/14/2941 |
| _version_ | 1818018581954166784 |
|---|---|
| author | Donghwoon Kwon Ritesh Malaiya Geumchae Yoon Jeong-Tak Ryu Su-Young Pi |
| author_facet | Donghwoon Kwon Ritesh Malaiya Geumchae Yoon Jeong-Tak Ryu Su-Young Pi |
| author_sort | Donghwoon Kwon |
| collection | DOAJ |
| description | One of the recent news headlines is that a pedestrian was killed by an autonomous vehicle because safety features in this vehicle did not detect an object on a road correctly. Due to this accident, some global automobile companies announced plans to postpone development of an autonomous vehicle. Furthermore, there is no doubt about the importance of safety features for autonomous vehicles. For this reason, our research goal is the development of a very safe and lightweight camera-based blind spot detection system, which can be applied to future autonomous vehicles. The blind spot detection system was implemented in open source software. Approximately 2000 vehicle images and 9000 non-vehicle images were adopted for training the Fully Connected Network (FCN) model. Other data processing concepts such as the Histogram of Oriented Gradients (HOG), heat map, and thresholding were also employed. We achieved 99.43% training accuracy and 98.99% testing accuracy of the FCN model, respectively. Source codes with respect to all the methodologies were then deployed to an off-the-shelf embedded board for actual testing on a road. Actual testing was conducted with consideration of various factors, and we confirmed 93.75% average detection accuracy with three false positives. |
| first_indexed | 2024-04-14T07:41:34Z |
| format | Article |
| id | doaj.art-9db7902fadc24f0fba2a20d9ce1509a6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-14T07:41:34Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9db7902fadc24f0fba2a20d9ce1509a62022-12-22T02:05:28ZengMDPI AGApplied Sciences2076-34172019-07-01914294110.3390/app9142941app9142941A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning MethodologyDonghwoon Kwon0Ritesh Malaiya1Geumchae Yoon2Jeong-Tak Ryu3Su-Young Pi4Department of Computer Science, Rockford University, Rockford, IL 61108, USASchool of Behavioral and Brain Sciences, University of Texas-Dallas, Richardson, TX 75080, USAASTI Manufacturing Ltd., Farmers Branch, TX 75234, USASchool of Electronic and Communication Engineering, Daegu University, Gyeongsan-si 38453, KoreaDepartment of Francisco College, Catholic University of Daegu, Gyeongsan-si 38430, KoreaOne of the recent news headlines is that a pedestrian was killed by an autonomous vehicle because safety features in this vehicle did not detect an object on a road correctly. Due to this accident, some global automobile companies announced plans to postpone development of an autonomous vehicle. Furthermore, there is no doubt about the importance of safety features for autonomous vehicles. For this reason, our research goal is the development of a very safe and lightweight camera-based blind spot detection system, which can be applied to future autonomous vehicles. The blind spot detection system was implemented in open source software. Approximately 2000 vehicle images and 9000 non-vehicle images were adopted for training the Fully Connected Network (FCN) model. Other data processing concepts such as the Histogram of Oriented Gradients (HOG), heat map, and thresholding were also employed. We achieved 99.43% training accuracy and 98.99% testing accuracy of the FCN model, respectively. Source codes with respect to all the methodologies were then deployed to an off-the-shelf embedded board for actual testing on a road. Actual testing was conducted with consideration of various factors, and we confirmed 93.75% average detection accuracy with three false positives.https://www.mdpi.com/2076-3417/9/14/2941blind spot detectiondeep learninginternet of thingsembedded board |
| spellingShingle | Donghwoon Kwon Ritesh Malaiya Geumchae Yoon Jeong-Tak Ryu Su-Young Pi A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology Applied Sciences blind spot detection deep learning internet of things embedded board |
| title | A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology |
| title_full | A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology |
| title_fullStr | A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology |
| title_full_unstemmed | A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology |
| title_short | A Study on Development of the Camera-Based Blind Spot Detection System Using the Deep Learning Methodology |
| title_sort | study on development of the camera based blind spot detection system using the deep learning methodology |
| topic | blind spot detection deep learning internet of things embedded board |
| url | https://www.mdpi.com/2076-3417/9/14/2941 |
| work_keys_str_mv | AT donghwoonkwon astudyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT riteshmalaiya astudyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT geumchaeyoon astudyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT jeongtakryu astudyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT suyoungpi astudyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT donghwoonkwon studyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT riteshmalaiya studyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT geumchaeyoon studyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT jeongtakryu studyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology AT suyoungpi studyondevelopmentofthecamerabasedblindspotdetectionsystemusingthedeeplearningmethodology |