This study presents an accident detection system leveraging the YOLOv3 model for real-time identification of head-on collisions, rear-end collisions, and vehicle rollovers. The YOLOv3 model was trained and fine-tuned on a unique dataset of accident photos following pre-training on the COCO dataset. Utilizing bounding box methodology, collisions were detected with high accuracy, achieving an average precision of 94% for vehicle rollovers, 92% for head-on collisions, and 93% for rear-end collisions. Remarkably the system performs in real-time, averaging 0.03 seconds for each frame of processing. By advancing technological innovation in accident detection systems, this research significantly contribute to the SDG 9. Moreover, its integration into intelligent transportation systems holds promise for enhancing infrastructure efficiency and safety. The proposed system represents a crucial step towards improving road safety, ultimately contributing to the advancement of sustainable infrastructure and innovation in transportation.

1.
J.
Redmon
, and
A.
Farhadi
, “
YoloV3 :An incremental improvement
,”
computer vision at Design Recognition
, arXiv preprint arXiv:1804.02767,
2018
.
2.
G.E.
Hinton
,
A.
Krizhevsky
and
I.
Sutkever
, “
Imagnet Classifications with the Deep Convolutional Neural Network
,”
Advances in neural information processing systems
,(pp.
1097
1105
).
3.
J.
Donahue
,
T.
Darrell
,
R.
Girshick
, and
J.
Malik
, “
Rich featureHierarchies for Accurate Object Detection and Semantic Segmentation
, ”
Proceedings of the IEEE conference on cvpr
, (pp
580
587
),
2017
.
4.
J.
Huang
,
V.
Rathod
,
C.
Sun
, M. Zhu.,
A.
Koratikara
,
A.
Fatthi
, and
K.
Murphy
, “
Speed/accuracy trade-offs for the modern convolutional object detectors
,”
In Proceedings of the IEEE cvpr
, (pp
7310
7311
),
2018
.
5.
M. T.
Law
,
J.
Deng
., “
Cornernet: objects detecting as pairred keypointts
,”
In Proceedings of the ECCV
,” (pp.
734-750
),
2018
.
6.
Y.
Li
,
J.
Huang
, and
W.
Yang
, “
Object detection in videos: A survey and a practical guide
,” arXiv preprint arXiv:2103.01656,
2021
.
7.
T. Y.
Lin
,
R.
Girshick
,
P.
Goyal
,
P.
Dollár
and
K.
He
, “
Focal loss of the dense object detection
,” In
Proceedings of the ICCV
,” (pp.
2980
2988
),
2021
Y.
Ma
, and
Y.
Zhang
, “
Deep learning for object detection: Acomprehensivereview
,”
Neurocomputing
,
441
,
289
302
.
8.
Y.
Ma
, and
Y.
Zhang
,
“Deep Learning for Object Detection:AComprehensiveReview
,
Neurocomputing
,
441
,
289
302
.
9.
R.
Girshick
,
S.
Ren
,
K.
He
and
J.
Sun
, “
FasterR-CNN:Towardsreal-time the Object Detection with Region Proposal Network
,”
In Advance NIPS
, (pp.
91
99
),
2021
.
10.
A.
Gupta
and
X.
Wang
, “
Videos as Space Time Region Graphs
,” In
Proceedings of the ECCV
, (pp.
399
417
).
11.
K. J.
Mohan
,
V. R.
Kanakala
and
V. K.
Reddy
, “
Modelling a Deep Network using CNN and RNN for Accident Classification
,”
In Measurement: Sensors
, Volume
27
,
100794
, June
2023
.
12.
H.
Wang
,
L.
Zhang
,
S.
Chen
,
X.
Wang
,
H.
Wang
,
K.
Zheng
and
H.
Wang
, “
Vehicle and Object Detection Based on Improved RetinaNet
,”
In JPCS
,
1757
(
1
):
012070
.
13.
H. Tae
Choi
,
H.
Kang
,
S.
Yu
,
H. J.
Lee
and
H. H.
Park
, “
SSD-EMB: An improved version SSD using enhanced feature map block for object sdetection
,”
In School of EEE, Chung-Ang University
, Seoul06974,
Korea
.
14.
J.
Smith
,
E.
Johnson
and
D.
Lee
, “
Real-Time Traffic Accident Detection and Classification Using Deep Learning
,” In
IEEE ITSS
, February
2020
.
15.
S.
Adams
and
M.
Brown
, "
Accident Detection and Response System for Intelligent Transportation Systems: A Review
," In
Journal of Intelligent Transportation Systems
, September
2019
.
16.
V.
Kanakala
,
K. J.
Mohan
,
V.
Krishna
, “
Modelling a Deep network using the CNN Network and RNN for accident classification
,”
in Measurements: Sensors
, Volume
27
, June
2023
,
100794
.
17.
L.
Zhang
,
H.
Wang
,
X.
Wang
,
S.
Chen
, H., Wang,
K.
Zheng
and
H.
wang
, “
Vehicle Object Detection Based on Improved RetinaNet
,” In
Journal of Physics Conference Series
1757
(
1
):
012070
.
18.
H.
Choi
,
H-Jun
Lee
,
H.
Kang
,
S.
Yu
and
H.
Park
, “
SSD-EMB: An Improved SSD Using the Enhanced Map Block for Object Detection
” In
School of EEE, Chung-Anng University
, Seoul 06974,
Korea
.
This content is only available via PDF.
You do not currently have access to this content.