Next Article in Journal
A Model-Driven Co-Design Framework for Fusing Control and Scheduling Viewpoints
Previous Article in Journal
Three-Level De-Multiplexed Dual-Branch Complex Delta-Sigma Transmitter
Previous Article in Special Issue
An Improved Calibration Method for a Rotating 2D LIDAR System
Open AccessArticle

Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database

1
National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan
2
Department of Electronics and Electrical Engineering, Keio University, Yokohama 223-8522, Japan
3
Tokyo Metropolitan University, Tokyo 192-0364, Japan
4
National Traffic Safety and Environment Laboratory, Tokyo 182-0012, Japan
*
Author to whom correspondence should be addressed.
Sensors 2018, 18(2), 627; https://doi.org/10.3390/s18020627
Received: 5 January 2018 / Revised: 7 February 2018 / Accepted: 8 February 2018 / Published: 20 February 2018
(This article belongs to the Special Issue Sensors for Transportation)
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. View Full-Text
Keywords: fine-grained pedestrian action recognition; two-stream convnets; driving recorder; advanced driver-assistance systems (ADAS) fine-grained pedestrian action recognition; two-stream convnets; driving recorder; advanced driver-assistance systems (ADAS)
Show Figures

Figure 1

MDPI and ACS Style

Kataoka, H.; Satoh, Y.; Aoki, Y.; Oikawa, S.; Matsui, Y. Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database. Sensors 2018, 18, 627. https://doi.org/10.3390/s18020627

AMA Style

Kataoka H, Satoh Y, Aoki Y, Oikawa S, Matsui Y. Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database. Sensors. 2018; 18(2):627. https://doi.org/10.3390/s18020627

Chicago/Turabian Style

Kataoka, Hirokatsu; Satoh, Yutaka; Aoki, Yoshimitsu; Oikawa, Shoko; Matsui, Yasuhiro. 2018. "Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database" Sensors 18, no. 2: 627. https://doi.org/10.3390/s18020627

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop