A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Real Time Implementation of the Saliency-Based Model of Visual Attention on a SIMD Architecture
Proceedings of the 24th DAGM Symposium on Pattern Recognition
A GPU based saliency map for high-fidelity selective rendering
AFRIGRAPH '06 Proceedings of the 4th international conference on Computer graphics, virtual reality, visualisation and interaction in Africa
2006 Special Issue: Modeling attention to salient proto-objects
Neural Networks
Applying computational tools to predict gaze direction in interactive visual environments
ACM Transactions on Applied Perception (TAP)
Computational visual attention systems and their cognitive foundations: A survey
ACM Transactions on Applied Perception (TAP)
Environment adapted active multi-focal vision system for object detection
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Autonomous switching of top-down and bottom-up attention selection for vision guided mobile robots
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Autonomous behavior-based switched top-down and bottom-up visual attention for mobile robots
IEEE Transactions on Robotics
Accelerators for biologically-inspired attention and recognition
Proceedings of the 50th Annual Design Automation Conference
GPU video retargeting with parallelized SeamCrop
Proceedings of the 5th ACM Multimedia Systems Conference
Hi-index | 0.00 |
In this paper a novel implementation of the saliency map model on a multi-GPU platform using CUDA technology is presented. The saliency map model is a well-known computational model for bottom-up attention selection and serves as a basis of many attention control strategies of cognitive vision systems. A real-time implementation is the prerequisite of an application of bottom-up attention on mobile robots and vehicles. Parallel computation on Graphics Processing Unit (GPU) provides an excellent solution for this kind of compute-intensive image processing. Running on 1 to 4 NVIDIA GeForce 8800 (GTX) graphics cards a frame rate of 313 fps at resolution of 640 × 480 is achieved, which is approximately 8.5 times faster than the standard implementations on CPUs. The implementation is also evaluated using a high-speed camera at 200 Hz. Using two GPUs only 2 ms extra computational time for the saliency map generation in addition to the camera capture time is required for images of 640 × 480 pixels.