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

Katrolia, Jigyasa Singh; Mirbach, Bruno; El-Sherif, Ahmed; Feld, Hartmut; Rambach, Jason; Stricker, Didier

doi:10.48550/arxiv.2103.11719

Cited by 6 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to them, AI has enabled a new range of applications and assistance in the vehicle cabin. A dataset of in-car cabin monitoring for vehicle interior monitoring is published by Katrolia et al in [35]. They have used a single wide-angle depth camera to collect in-car datasets for various scenarios.…”

Section: Related Workmentioning

confidence: 99%

In-Cabin Monitoring System for Autonomous Vehicles

Mishra

Lee

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

In this paper, we have demonstrated a robust in-cabin monitoring system (IMS) for safety, security, surveillance, and monitoring, including privacy concerns for personal and shared autonomous vehicles (AVs). It consists of a set of monitoring cameras and an onboard device (OBD) equipped with artificial intelligence (AI). Hereafter, this combination of a camera and an OBD is referred to as the AI camera. We have investigated the issues for mobility services in higher levels of autonomous driving, what needs to be monitored, how to monitor, etc. Our proposed IMS is an on-device AI system that indigenously has improved the privacy of the users. Furthermore, we have enlisted the essential actions to be considered in an IMS and developed an appropriate database (DB). Our DB consists of multifaced scenarios important for monitoring the in-cabin of the higher-level AVs. Moreover, we have compared popular AI models applied for object and occupant recognition. In addition, our DB is available on request to support the research on the development of seamless monitoring of the in-cabin higher levels of autonomous driving for the assurance of safety and security.

show abstract

Section: Related Workmentioning

confidence: 99%

In-Cabin Monitoring System for Autonomous Vehicles

Mishra

Lee

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Publicly available realistic datasets for the vehicle interior are scarce. Some exceptions are the recently released AutoPOSE [60] and DriveAHead [61] datasets for driver head orientation and position, Drive&Act [62] a multi modal benchmark for action recognition in automated vehicles and TICaM [63] for activity recognition and person detection. However, these datasets provide images for a single vehicle interior only.…”

Section: Related Workmentioning

confidence: 99%

Autoencoder and Partially Impossible Reconstruction Losses

Cruz

Taetz

Stifter³

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

The generally unsupervised nature of autoencoder models implies that the main training metric is formulated as the error between input images and their corresponding reconstructions. Different reconstruction loss variations and latent space regularizations have been shown to improve model performances depending on the tasks to solve and to induce new desirable properties such as disentanglement. Nevertheless, measuring the success in, or enforcing properties by, the input pixel space is a challenging endeavour. In this work, we want to make use of the available data more efficiently and provide design choices to be considered in the recording or generation of future datasets to implicitly induce desirable properties during training. To this end, we propose a new sampling technique which matches semantically important parts of the image while randomizing the other parts, leading to salient feature extraction and a neglection of unimportant details. The proposed method can be combined with any existing reconstruction loss and the performance gain is superior to the triplet loss. We analyse the resulting properties on various datasets and show improvements on several computer vision tasks: illumination and unwanted features can be normalized or smoothed out and shadows are removed such that classification or other tasks work more reliably; a better invariances with respect to unwanted features is induced; the generalization capacities from synthetic to real images is improved, such that more of the semantics are preserved; uncertainty estimation is superior to Monte Carlo Dropout and an ensemble of models, particularly for datasets of higher visual complexity. Finally, classification accuracy by means of simple linear classifiers in the latent space is improved compared to the triplet loss. For each task, the improvements are highlighted on several datasets commonly used by the research community, as well as in automotive applications.

show abstract

“…This makes it more difficult to refine facial depth. With the advancement of the autonomous industry, it is essential to monitor the driver of a vehicle in order to achieve safety, comfort, and enhanced human-machine interactions [10]. As a proof of concept, the depth estimation in the intelligent vehicle's monitoring system is an advanced way to analyze the driver's behaviour in 3 dimensional instead of 2-dimensional environments.…”

Section: Introductionmentioning

confidence: 99%

A Robust Light-Weight Fused-Feature Encoder-Decoder Model for Monocular Facial Depth Estimation From Single Images Trained on Synthetic Data

et al. 2023

View full text Add to dashboard Cite

Due to the real-time acquisition and reasonable cost of consumer cameras, monocular depth maps have been employed in a variety of visual applications. Regarding ongoing research in depth estimation, they continue to suffer from low accuracy and enormous sensor noise. To improve the prediction of depth maps, this paper proposed a lightweight neural facial depth estimation model based on single image frames. Following a basic encoder-decoder network design, the features are extracted by initializing the encoder with a high-performance pre-trained network and reconstructing high-quality facial depth maps with a simple decoder. The model can employ pixel representations and recover full details in terms of facial features and boundaries by employing a feature fusion module. When tested and evaluated across four public facial depth datasets, the suggested network provides more reliable and state-of-the-art results, with significantly less computational complexity and a reduced number of parameters. The training procedure is primarily based on the use of synthetic human facial images, which provide a consistent ground truth depth map, and the employment of an appropriate loss function leads to higher performance. Numerous experiments have been performed to validate and demonstrate the usefulness of the proposed approach. Finally, the model performs better than existing comparative facial depth networks in terms of generalization ability and robustness across different test datasets, setting a new baseline method for facial depth maps.

show abstract

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

Cited by 6 publications

References 13 publications

In-Cabin Monitoring System for Autonomous Vehicles

In-Cabin Monitoring System for Autonomous Vehicles

Autoencoder and Partially Impossible Reconstruction Losses

A Robust Light-Weight Fused-Feature Encoder-Decoder Model for Monocular Facial Depth Estimation From Single Images Trained on Synthetic Data

Contact Info

Product

Resources

About