• Corpus ID: 232307120

TICaM: A Time-of-flight In-car Cabin Monitoring Dataset

@inproceedings{Katrolia2021TICaMAT,
  title={TICaM: A Time-of-flight In-car Cabin Monitoring Dataset},
  author={Jigyasa Katrolia and Bruno Mirbach and Ahmed El-Sherif and Hartmut Feld and Jason R. Rambach and Didier Stricker},
  booktitle={BMVC},
  year={2021}
}
We present TICaM, a Time-of-flight In-car Cabin Monitoring dataset for vehicle interior monitoring using a single wide-angle depth camera. Our dataset goes beyond currently available in-car cabin datasets in terms of the ambit of labeled classes, recorded scenarios and annotations provided; all at the same time. We recorded an exhaustive list of actions performed while driving and provide for them multi-modal labeled images (depth, RGB and IR), with complete annotations for 2D and 3D object… 

Figures and Tables from this paper

Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoring
TLDR
This work proposes the first multitask network solving all these three tasks jointly in the area of occupancy monitoring, and allows a flexible combination of the three mentioned tasks during a simple end-to-end training.
Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification
TLDR
An investigation on the SVIRO dataset for occupant classification on the rear bench is performed and an autoencoder based approach is proposed to improve the transferability and is on par with commonly used classification models when trained from scratch and sometimes out-performs models pre-trained on a large amount of data.
Semantic Segmentation in Depth Data: A Comparative Evaluation of Image and Point Cloud Based Methods
TLDR
This paper extensively compare various semantic segmentation algorithms and offers analysis of the performance and computational cost of these algorithms that can provide guidelines on when each method should be preferred.
Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes
TLDR
A new sampling technique is demonstrated, which matches semantically important parts of the image, while randomizing the other parts, leads to salient feature extraction and a neglection of unimportant parts, which helps the generalization to real data.
Autoencoder and Partially Impossible Reconstruction Losses
TLDR
A new sampling technique is proposed which matches semantically important parts of the image while randomizing the other parts, leading to salient feature extraction and a neglection of unimportant details, which can be combined with any existing reconstruction loss and the performance gain is superior to the triplet loss.
From Driver Talk To Future Action: Vehicle Maneuver Prediction by Learning from Driving Exam Dialogs
TLDR
This work proposes a technique for automatic detection of smalltalk based on the likelihood of spoken words being present in everyday dialogs and presents the first automated framework for anticipating driver intention by learning from recorded driving exam conversations.
In-Cabin Monitoring System for Autonomous Vehicles
TLDR
This paper has demonstrated a robust in-cabin monitoring system for safety, security, surveillance, and monitoring, including privacy concerns for personal and shared autonomous vehicles (AVs), and enlisted the essential actions to be considered and developed an appropriate database (DB).
TIMo—A Dataset for Indoor Building Monitoring with a Time-of-Flight Camera
TLDR
TIMo (Time- of-flight Indoor Monitoring), a dataset for video-based monitoring of indoor spaces captured using a time-of-flight (ToF) camera, which addresses the gap in the landscape of surveillance video datasets.

References

SHOWING 1-10 OF 22 REFERENCES
SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark
We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles, in order to analyze machine learning-based approaches for their generalization capacities
DFKI Cabin Simulator: A Test Platform for Visual In-Cabin Monitoring Functions
TLDR
The test platform is based on a driving simulator developed at the DFKI, consisting of a realistic in-cabin mock-up and a wide-angle projection system for a realistic driving experience, and will be the basis for the creation of large-scale in-Cabin benchmark datasets.
In-Vehicle Occupancy Detection With Convolutional Networks on Thermal Images
TLDR
It is shown that the proposed tiny convolutional model to count on-board passengers surpasses state-of-the-art methods in classification and has comparable performance in detection and is suitable for deployment on embedded platforms.
Driver Gaze Zone Dataset With Depth Data
  • R. F. RibeiroP. D. P. Costa
  • Computer Science, Environmental Science
    2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
  • 2019
TLDR
A novel public dataset designed to train algorithms that estimate driver gaze zone in real driving conditions and the largest one available and the only one that provides 2D and 3D data aligned at pixel using a Intel® RealSense™ camera is presented.
A Framework for Detecting Vehicle Occupancy Based on the Occupant Labeling Method
TLDR
This study proposes an overall framework for an algorithm that effectively detects occupants in vehicles using photographic data and applies a new data labeling method that enables highly accurate occupant detection even with a small amount of data.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
YOLACT: Real-Time Instance Segmentation
We present a simple, fully-convolutional model for real-time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan Xp, which is significantly faster than any
Head, Eye, and Hand Patterns for Driver Activity Recognition
TLDR
A multiview, multimodal vision framework is proposed in order to characterize driver activity based on head, eye, and hand cues to allow for a richer description of the driver's state and for improved activity detection performance.
Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models
TLDR
This work proposes an Autoregressive Input-Output HMM to model the contextual information alongwith the maneuvers in driving maneuvers and shows that it can anticipate maneuvers 3.5 seconds before they occur with over 80% F1-score in real-time.
Real-time Distracted Driver Posture Classification
TLDR
A genetically-weighted ensemble of Convolutional Neural Networks using a genetic algorithm yields in better classification confidence and is presented as a thinned version of the ensemble that could achieve a 94.29% classification accuracy and operate in a realtime environment.
...
...