Litcius/Paper detail

Improving Driver Gaze Prediction With Reinforced Attention

Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, Liang Zheng

2020IEEE Transactions on Multimedia48 citationsDOIOpen Access PDF

Abstract

We consider the task of driver gaze prediction: estimating where the location of the focus of a driver should be, based on a raw video of the outside environment. In practice, we output a probability map that gives the normalized probability of each point in a given scene being the object of the driver attention. Most existing methods ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Coarse-to-Fine</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-branch</i> ) take an image or a video as input and directly output the fixation map. While successful, these methods can often produce highly scattered predictions, rendering them unreliable for real-world usage. Motivated by this observation, we propose the reinforced attention (RA) model as a regulatory mechanism to increase prediction density. Our method is built directly on top of existing methods, making it complementary to current approaches. Specifically, we first use <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-branch</i> to obtain an initial fixation map. Then, RA is trained using deep reinforcement learning to learn a location prediction policy, producing a reinforced attention. Finally, in order to obtain the final gaze prediction result, we combine the fixation map and the reinforced attention by a mask-guided multiplication. Experimental results show that our framework improves the accuracy of gaze prediction, and provides state-of-the-art performance on the DR(eye)VE dataset.

Topics & Concepts

Computer scienceGazeArtificial intelligenceReinforcement learningFixation (population genetics)Rendering (computer graphics)Machine learningComputer visionDemographySociologyPopulationGaze Tracking and Assistive TechnologyVisual Attention and Saliency DetectionVideo Surveillance and Tracking Methods
Improving Driver Gaze Prediction With Reinforced Attention | Litcius