Blind Spot Monitoring in Light Vehicles — System Performance

Sensors are the quintessential part of Blind Spot Detection (BSD) systems, which have a profound effect on the performance of the system. Every sensor has its unique deficiencies that can deteriorate the performance of the system under grievous circumstances. Hence, making vital tasks in BSD such as object detection arduous. Indeed, previous studies have demonstrated that data fusion techniques can diminish the adverse effects of sensors and improve detection accuracy in the BSD system. One of the main advantages of data fusion is to improve detection accuracy and reduce the processing time by multiple sensors cooperation. We propose a BSD model that objects are detected in consecutive time intervals in the BSD system. Then, association techniques are employed for multi-sensor fusion since all sensors data are not ordinarily ready for fusion simultaneously. It should be noted that the orthodox approach in data association techniques in BSD often includes a global nearest neighbor, joint probabilistic data association, and multiple hypothesis tests. We simulate and compare these techniques by tracking multiple targets and multi-sensor fusion using virtual data in MATLAB. Furthermore, we illustrate that our multi-sensor fusion detection accuracy in the BSD system is augmented compared to a single sensor BSD system.

Blind Spot Detection System in Vehicles Using Fusion of Radar Detections and Camera Verification

With the rapidly increasing of automobiles, traffic accidents are gradually becoming more frequent. This creates a great need for effective traffic anomaly detection algorithms. Existing methods shed light on directly inferring the abnormalities from traffic flow, which is short in features extraction and representation of traffic flows. In this paper, we propose three new traffic flow features, namely the road congestion, the traffic intensity, and the traffic state instability, for more comprehensive traffic status representation and anomaly detection. Residual analysis, quadratic discrimination, multi-resolution wavelet analysis are integrated for the extraction of the aforementioned features, which will be applied for the downstream tasks of traffic anomaly detection. Experimental results reveal that accident identification based on the proposed features is more effective than the raw traffic flow, which is supposed to provide an alternative approach for further applications and studies. 

/pdf/a-novel-traffic-accident-detection-method-with-comprehensive-17r1pbmo.pdf

A novel traffic accident detection method with comprehensive traffic flow features extraction

Today’s methods for uncovering causal relationships from observational data either constrain functional assignments (linearity/additive noise assumptions) or the data generating process (e.g

Jacobian-based Causal Discovery with Nonlinear ICA

Trajectory prediction is critical for autonomous driving vehicles. Most existing methods tend to model the correlation between history trajectory (input) and future trajectory (output). Since correlation is just a superficial description of reality, these methods rely heavily on the i.i.d. assumption and evince a heightened susceptibility to out-of-distribution data. To address this problem, we propose an Out-of- Distribution Causal Graph (OOD-CG), which explicitly defines the underlying causal structure of the data with three entangled latent features: 1) domain-invariant causal feature (IC), 2) domain-variant causal feature (VC), and 3) domain-variant non-causal feature (VN ). While these features are confounded by confounder (C) and domain selector (D). To leverage causal features for prediction, we propose a Causal Inspired Learning Framework (CILF), which includes three steps: 1) extracting domain-invariant causal feature by means of an invariance loss, 2) extracting domain variant feature by domain contrastive learning, and 3) separating domain-variant causal and non-causal feature by encouraging causal sufficiency. We evaluate the performance of CILF in different vehicle trajectory prediction models on the mainstream datasets NGSIM and INTERACTION. Experiments show promising improvements in CILF on domain generalization.

CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction

Sensor selection is an essential aspect of blind spot detection (BSD) systems. Indeed, we must choose the sensors appropriately to accomplish high accuracy and performance in any driving condition. Each sensor has exclusive properties which are suitable for a few specific circumstances. Therefore, a comprehensive study is warranted to determine the optimum number of sensors and the type of sensors for BSD. Although sensors have some deficiencies which can deteriorate the whole system's performance, a combination of multiple types of sensors together with data fusion methods in most cases can substantially compensate for sensors imperfection. In this paper, we have concentrated on multi-sensor fusion in BSD system and its advantages which cannot be achieved in a single-sensor BSD system. A sensing structure for the BSD system is proposed considering the indispensable factors in BSD coupled with sensors constraints, features, and specifications.

Sensing Structure for Blind Spot Detection System in Vehicles

Conventional supervised learning methods typically assume i.i.d samples and are found to be sensitive to out-of-distribution (OOD) data. We propose Generative Causal Representation Learning (GCRL) which leverages causality to facilitate knowledge transfer under distribution shifts. While we evaluate the effectiveness of our proposed method in human trajectory prediction models, GCRL can be applied to other domains as well. First, we propose a novel causal model that explains the generative factors in motion forecasting datasets using features that are common across all environments and with features that are specific to each environment. Selection variables are used to determine which parts of the model can be directly transferred to a new environment without fine-tuning. Second, we propose an end-to-end variational learning paradigm to learn the causal mechanisms that generate observations from features. GCRL is supported by strong theoretical results that imply identifiability of the causal model under certain assumptions. Experimental results on synthetic and real-world motion forecasting datasets show the robustness and effectiveness of our proposed method for knowledge transfer under zero-shot and low-shot settings by substantially outperforming the prior motion forecasting models on out-of-distribution prediction. Our code is available at https://github.com/sshirahmad/GCRL.

Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting

Automatic detection of traffic accidents has a crucial effect on improving transportation, public safety, and path planning. Many lives can be saved by the consequent decrease in the time between when the accidents occur and when rescue teams are dispatched, and much travelling time can be saved by notifying drivers to select alternative routes. This problem is challenging mainly because of the rareness of accidents and spatial heterogeneity of the environment. This paper studies deep representation of loop detector data using Long-Short Term Memory (LSTM) network for automatic detection of freeway accidents. The LSTM-based framework increases class separability in the encoded feature space while reducing the dimension of data. Our experiments on real accident and loop detector data collected from the Twin Cities Metro freeways of Minnesota demonstrate that deep representation of traffic flow data using LSTM network has the potential to detect freeway accidents in less than 18 minutes with a true positive rate of 0.71 and a false positive rate of 0.25 which outperforms other competing methods in the same arrangement.

Shayan Shirahmad Gale Bagi

Papers

Sensing Structure for Blind Spot Detection System in Vehicles

Blind Spot Detection System in Vehicles Using Fusion of Radar Detections and Camera Verification

Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting

Deep Representation of Imbalanced Spatio-temporal Traffic Flow Data for Traffic Accident Detection