Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database
- PMID: 29461473
- PMCID: PMC5855092
- DOI: 10.3390/s18020627
Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database
Abstract
The paper presents an emerging issue of fine-grained pedestrian action recognition that induces an advanced pre-crush safety to estimate a pedestrian intention in advance. The fine-grained pedestrian actions include visually slight differences (e.g., walking straight and crossing), which are difficult to distinguish from each other. It is believed that the fine-grained action recognition induces a pedestrian intention estimation for a helpful advanced driver-assistance systems (ADAS). The following difficulties have been studied to achieve a fine-grained and accurate pedestrian action recognition: (i) In order to analyze the fine-grained motion of a pedestrian appearance in the vehicle-mounted drive recorder, a method to describe subtle change of motion characteristics occurring in a short time is necessary; (ii) even when the background moves greatly due to the driving of the vehicle, it is necessary to detect changes in subtle motion of the pedestrian; (iii) the collection of large-scale fine-grained actions is very difficult, and therefore a relatively small database should be focused. We find out how to learn an effective recognition model with only a small-scale database. Here, we have thoroughly evaluated several types of configurations to explore an effective approach in fine-grained pedestrian action recognition without a large-scale database. Moreover, two different datasets have been collected in order to raise the issue. Finally, our proposal attained 91.01% on National Traffic Science and Environment Laboratory database (NTSEL) and 53.23% on the near-miss driving recorder database (NDRDB). The paper has improved +8.28% and +6.53% from baseline two-stream fusion convnets.
Keywords: advanced driver-assistance systems (ADAS); driving recorder; fine-grained pedestrian action recognition; two-stream convnets.
Conflict of interest statement
The authors declare no conflicts of interest.
Figures
Similar articles
-
Creating pedestrian crash scenarios in a driving simulator environment.Traffic Inj Prev. 2015;16 Suppl 1:S12-7. doi: 10.1080/15389588.2015.1015001. Traffic Inj Prev. 2015. PMID: 26027964
-
On-Board Detection of Pedestrian Intentions.Sensors (Basel). 2017 Sep 23;17(10):2193. doi: 10.3390/s17102193. Sensors (Basel). 2017. PMID: 28946632 Free PMC article.
-
A novel framework to evaluate pedestrian safety at non-signalized locations.Accid Anal Prev. 2018 Feb;111:23-33. doi: 10.1016/j.aap.2017.11.015. Accid Anal Prev. 2018. PMID: 29169102
-
A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction.Sensors (Basel). 2021 Nov 13;21(22):7543. doi: 10.3390/s21227543. Sensors (Basel). 2021. PMID: 34833619 Free PMC article. Review.
-
[Primary prevention measures for controlling pedestrian injuries and deaths and improving road safety].Rev Salud Publica (Bogota). 2010 Jun;12(3):497-509. Rev Salud Publica (Bogota). 2010. PMID: 21311837 Review. Spanish.
Cited by
-
Representation Learning for Fine-Grained Change Detection.Sensors (Basel). 2021 Jun 30;21(13):4486. doi: 10.3390/s21134486. Sensors (Basel). 2021. PMID: 34209075 Free PMC article. Review.
-
Multiple Event-Based Simulation Scenario Generation Approach for Autonomous Vehicle Smart Sensors and Devices.Sensors (Basel). 2019 Oct 14;19(20):4456. doi: 10.3390/s19204456. Sensors (Basel). 2019. PMID: 31615164 Free PMC article.
-
A Comprehensive Survey of Driving Monitoring and Assistance Systems.Sensors (Basel). 2019 Jun 6;19(11):2574. doi: 10.3390/s19112574. Sensors (Basel). 2019. PMID: 31174275 Free PMC article. Review.
-
Estimation of Driver's Danger Level when Accessing the Center Console for Safe Driving.Sensors (Basel). 2018 Oct 10;18(10):3392. doi: 10.3390/s18103392. Sensors (Basel). 2018. PMID: 30309040 Free PMC article.
-
Action Recognition by an Attention-Aware Temporal Weighted Convolutional Neural Network.Sensors (Basel). 2018 Jun 21;18(7):1979. doi: 10.3390/s18071979. Sensors (Basel). 2018. PMID: 29933555 Free PMC article.
References
-
- Benenson R., Omran M., Hosang J., Schiele B. Ten years of pedestrian detection, what have we learned?; Proceedings of the European Conference on Computer Vision Workshop (ECCVW); Zurich, Switzerland. 6–12 September 2014.
-
- Dalal N., Triggs B. Histograms of Oriented Gradients for Human Detection; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); San Diego, CA, USA. 20–25 June 2005; pp. 886–893.
-
- Viola P., Jones M. Rapid Object Detection using a Boosted Cascaded of Simple Features; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Kauai, HI, USA. 8–14 December 2001; pp. 511–518.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical