TUMTraf V2X Cooperative Perception Dataset

Cooperative perception offers several benefits for enhancing the capabilities of autonomous vehicles and improving road safety. Using roadside sensors in addition to onboard sensors increases reliability and extends the sensor range. External sensors offer higher situational awareness for automated vehicles and prevent occlusions. We propose CoopDet3D, a cooperative multi-modal fusion model, and TUMTraf-V2X, a perception dataset, for the cooperative 3D object detection and tracking task. Our dataset contains 2,000 labeled point clouds and 5,000 labeled images from five roadside and four onboard sensors. It includes 30k 3D boxes with track IDs and precise GPS and IMU data. We labeled eight categories and covered occlusion scenarios with challenging driving maneuvers, like traffic violations, near-miss events, overtaking, and U-turns. Through multiple experiments, we show that our CoopDet3D camera-LiDAR fusion model achieves an increase of +14.36 3D mAP compared to a vehicle camera-LiDAR fusion model. Finally, we make our dataset, model, labeling tool, and dev-kit publicly available on our website: https://tum-traffic-dataset.github.io/tumtraf-v2x.

Holistic Interpretation of Public Scenes Using Computer Vision and Temporal Graphs to Identify Social Distancing Violations

The COVID-19 pandemic has caused an unprecedented global public health crisis. Given its inherent nature, social distancing measures are proposed as the primary strategies to curb the spread of this pandemic. Therefore, identifying situations where these protocols are violated, has implications for curtailing the spread of the disease and promoting a sustainable lifestyle. This paper proposes a novel computer vision-based system to analyze CCTV footage to provide a threat level assessment of COVID-19 spread. The system strives to holistically capture and interpret the information content of CCTV footage spanning multiple frames to recognize instances of various violations of social distancing protocols, across time and space, as well as identification of group behaviors. This functionality is achieved primarily by utilizing a temporal graph-based structure to represent the information of the CCTV footage and a strategy to holistically interpret the graph and quantify the threat level of the given scene. The individual components are tested and validated on a range of scenarios and the complete system is tested against human expert opinion. The results reflect the dependence of the threat level on people, their physical proximity, interactions, protective clothing, and group dynamics. The system performance has an accuracy of 76%, thus enabling a deployable threat monitoring system in cities, to permit normalcy and sustainability in the society.

Hands Off: A Handshake Interaction Detection and Localization Model for COVID-19 Threat Control

The COVID-19 outbreak has affected millions of people across the globe and is continuing to spread at a drastic scale. Out of the numerous steps taken to control the spread of the virus, social distancing has been a crucial and effective practice. However, recent reports of social distancing violations suggest the need for non-intrusive detection techniques to ensure safety in public spaces. In this paper, a real-time detection model is proposed to identify handshake interactions in a range of realistic scenarios with multiple people in the scene and also detect multiple interactions in a single frame. This is the first work that performs dyadic interaction localization in a multi-person setting. The efficacy of the proposed model was evaluated across two different datasets on more than 3200 frames, thus enabling a robust localization model in different environments. The proposed model is the first dyadic interaction localizer in a multi-person setting, which enables it to be used in public spaces to identify handshake interactions and thereby identify and mitigate COVID-19 transmission.

A generalized forecasting solution to enable future insights of COVID-19 at sub-national level resolutions

COVID-19 continues to cause a significant impact on public health. To minimize this impact, policy makers undertake containment measures that however, when carried out disproportionately to the actual threat, as a result if errorneous threat assessment, cause undesirable long-term socio-economic complications. In addition, macro-level or national level decision making fails to consider the localized sensitivities in small regions. Hence, the need arises for region-wise threat assessments that provide insights on the behaviour of COVID-19 through time, enabled through accurate forecasts. In this study, a forecasting solution is proposed, to predict daily new cases of COVID-19 in regions small enough where containment measures could be locally implemented, by targeting three main shortcomings that exist in literature; the unreliability of existing data caused by inconsistent testing patterns in smaller regions, weak deploy-ability of forecasting models towards predicting cases in previously unseen regions, and model training biases caused by the imbalanced nature of data in COVID-19 epi-curves. Hence, the contributions of this study are three-fold; an optimized smoothing technique to smoothen less deterministic epi-curves based on epidemiological dynamics of that region, a Long-Short-Term-Memory (LSTM) based forecasting model trained using data from select regions to create a representative and diverse training set that maximizes deploy-ability in regions with lack of historical data, and an adaptive loss function whilst training to mitigate the data imbalances seen in epi-curves. The proposed smoothing technique, the generalized training strategy and the adaptive loss function largely increased the overall accuracy of the forecast, which enables efficient containment measures at a more localized micro-level.

An Optical physics inspired CNN approach for intrinsic image decomposition

Intrinsic Image Decomposition is an open problem of generating the constituents of an image. Generating reflectance and shading from a single image is a challenging task specifically when there is no ground truth. There is a lack of unsupervised learning approaches for decomposing an image into reflectance and shading using a single image. We propose a neural network architecture capable of this decomposition using physics-based parameters derived from the image. Through experimental results, we show that (a) the proposed methodology outperforms the existing deep learning-based IID techniques and (b) the derived parameters improve the efficacy significantly. We conclude with a closer analysis of the results (numerical and example images) showing several avenues for improvement.

A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.

Non-contact Infant Sleep Apnea Detection

Sleep apnea is a breathing disorder where a person repeatedly stops breathing in sleep. Early detection is crucial for infants because it might bring long term adversities. The existing accurate detection mechanism (pulse oximetry) is a skin contact measurement. The existing non-contact mechanisms (acoustics, video processing) are not accurate enough. This paper presents a novel algorithm for the detection of sleep apnea with video processing. The solution is non-contact, accurate and lightweight enough to run on a single board computer. The paper discusses the accuracy of the algorithm on real data, advantages of the new algorithm, its limitations and suggests future improvements.