Papers › On the safety of vulnerable road users by cyclist orientation detection using Deep Learning

On the safety of vulnerable road users by cyclist orientation detection using Deep Learning

25 Apr 2020arXiv:2004.11909archive 2025-07-28

Marichelo Garcia-Venegas, Diego A. Mercado-Ravell, Carlos A. Carballo-Monsivais

In this work, orientation detection using Deep Learning is acknowledged for a particularly vulnerable class of road users,the cyclists. Knowing the cyclists' orientation is of great relevance since it provides a good notion about their future trajectory, which is crucial to avoid accidents in the context of intelligent transportation systems. Using Transfer Learning with pre-trained models and TensorFlow, we present a performance comparison between the main algorithms reported in the literature for object detection,such as SSD, Faster R-CNN and R-FCN along with MobilenetV2, InceptionV2, ResNet50, ResNet101 feature extractors. Moreover, we propose multi-class detection with eight different classes according to orientations. To do so, we introduce a new dataset called "Detect-Bike", containing 20,229 cyclist instances over 11,103 images, which has been labeled based on cyclist's orientation. Then, the same Deep Learning methods used for detection are trained to determine the target's heading. Our experimental results and vast evaluation showed satisfactory performance of all of the studied methods for the cyclists and their orientation detection, especially using Faster R-CNN with ResNet50 proved to be precise but significantly slower. Meanwhile, SSD using InceptionV2 provided good trade-off between precision and execution time, and is to be preferred for real-time embedded applications.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

2D Cyclist DetectionObject DetectionTransfer Learningobject-detection

Datasets

Introduced by this paper, per the archive.

CIMAT-Cyclist

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Cyclist Detection CIMAT-Cyclist SSD InceptionV2 mAP@0.50 0.918 #1 of 2 Archive leaderboard report
2D Cyclist Detection CIMAT-Cyclist MobileNetV2 mAP@0.50 0.899 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAuxiliary ClassifierAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionFaster R-CNNGlobal Average PoolingInception ModuleInception v2Inverted Residual BlockKaiming InitializationMax PoolingNon Maximum SuppressionPointwise ConvolutionPosition-Sensitive RoI PoolingR-FCNRPNReLUResidual BlockResidual ConnectionRoIPoolSSDSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections