Multi-Task Driver Distraction Detection for Real-World Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver distraction detection systems using transfer learning approaches struggle with predicting distractions in real-world scenarios due to their inability to learn important image features, leading to poor performance and frequent false alarms.
Innovation Solution
A multi-task model is employed that simultaneously detects driver distraction, face, body, and upper-body landmarks using a unified network with multiple prediction heads, trained by minimizing a joint loss across these tasks, allowing for accurate distraction classification and extension to various distraction classes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If transfer learning approach is used with controlled environment datasets, then training efficiency is improved, but prediction accuracy on real-world images deteriorates
Solution Approach 1:
The patent changes the training parameters by using real-world datasets instead of controlled environment datasets, and employs a multi-task learning approach with different loss function weights to improve prediction accuracy while maintaining training efficiency
Solution Approach 2:
The patent implements a multi-task model that simultaneously performs distraction detection, mobile detection, face detection, and body detection, making the system universal across multiple detection functions and improving overall prediction accuracy on real-world images
2Measurement precision
If multi-task model is used with multiple prediction heads, then prediction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent segments the detection tasks into separate prediction heads (distraction detection head, mobile detection head, face detection head, body detection head), where each head specializes in one task while sharing the same backbone feature extractor, thus improving accuracy without excessive complexity increase
Solution Approach 2:
The patent merges multiple detection tasks into a unified multi-task model that shares common feature extraction layers, reducing overall model complexity compared to using separate models for each task while maintaining high prediction accuracy
Data Source
AI summary
Disclosed are a multi-task training technique and resulting model for detecting distracted driving. In one embodiment, a method is disclosed comprising inputting a plurality of labeled examples into a multi-task network, the multi-task network comprising: a backbone network, the backbone network generating one or more feature vectors corresponding to each of the labeled examples, and a plurality of prediction heads coupled to the backbone network; minimizing a joint loss based on outputs of the plurality of prediction heads, the minimizing the joint loss causing a change in parameters of the backbone network; and storing a distraction classification model after minimizing the joint loss, the distraction classification model comprising the parameters of the backbone network and parameters of at least one of the prediction heads.