Multimodal saliency-based attention: A lazy robot's approach

Abstract

Abstract-We extend our work on an integrated object-based system for saliency-driven overt attention and knowledge-driven object analysis. We present how we can reduce the amount of necessary head movement during scene analysis while still focusing all salient proto-objects in an order that strongly favors proto-objects with a higher saliency. Furthermore, we integrated motion saliency and as a consequence adaptive predictive gaze control to allow for efficient gazing behavior on the ARMAR-III robot head. To evaluate our approach, we first collected a new data set that incorporates two robotic platforms, three scenarios, and different scene complexities. Second, we introduce measures for the effectiveness of active overt attention mechanisms in terms of saliency cumulation and required head motion. This way, we are able to objectively demonstrate the effectiveness of the proposed multicriterial focus of attention selection.

Designing an artificial attention system for social robots

“…Additionally, overt attention (i.e. active perception) is still a challenging task in terms of design and quantitative evaluation, due to its scene-dependent nature [25], [26].…”

“Wow!” Bayesian surprise for salient acoustic event detection

“…In this paper, we extend our previous work with respect to two main aspects: First, we propose the use of the Gamma distribution instead of the previously applied Gaussian distribution. Second, we provide a quantitative evaluation, which nicely complements and substantially adds to our previous, mostly qualitative system evaluations (see [1,4,5]). …”

“…We primarily developed acoustic surprise to focus the computational resources and control the overt attention of (humanoid) robots, see Fig. 1, and smart environments (see [1,[3][4][5]). In such applications, acoustic surprise can serve two purposes: First, we can focus audio processing and, second, we can actively control the overt attention (i.e., the sensor orientation) to optimize the scene perception.…”

A Biologically Motivated, Proto-Object-Based Audiovisual Saliency Model

“…Extensions of this approach can be found in [42]. A work related to the one in [42] is presented in [43], where a weighted linear combination of proto-object representations obtained using mean-shift clustering is detailed. Even though the method uses linear combination, the authors did not use motion information in computing the visual saliency map.…”