Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision

Medathati, N. V. Kartheek; Neumann, Heiko; Masson, Guillaume S.; Kornprobst, Pierre

doi:10.1016/j.cviu.2016.04.009

Cited by 83 publications

(42 citation statements)

References 295 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has indeed been a cross-pollination in the two fields (e.g., [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21], [22], [23]). On the one hand, experimental paradigms and psychophysics tools in cognitive vision have been exploited to study the behavior of computer vision algorithms.…”

Section: Computer Vision and Biological Visionmentioning

confidence: 99%

Negative results in computer vision: A perspective

Borji

2018

Image and Vision Computing

View full text Add to dashboard Cite

A negative result is when the outcome of an experiment or a model is not what is expected or when a hypothesis does not hold. Despite being often overlooked in the scientific community, negative results are results and they carry value. While this topic has been extensively discussed in other fields such as social sciences and biosciences, less attention has been paid to it in the computer vision community. The unique characteristics of computer vision, particularly its experimental aspect, call for a special treatment of this matter. In this paper, I will address what makes negative results important, how they should be disseminated and incentivized, and what lessons can be learned from cognitive vision research in this regard. Further, I will discuss issues such as computer vision and human vision interaction, experimental design and statistical hypothesis testing, explanatory versus predictive modeling, performance evaluation, model comparison, as well as computer vision research culture.

show abstract

Section: Computer Vision and Biological Visionmentioning

confidence: 99%

Negative results in computer vision: A perspective

Borji

2018

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Computer scientists are mainly interested in solving single, distinct tasks (e.g., segmentation, recognition, etc. ), while, from the neuroscientific side, the visual system is considered as a general-purpose system that could adapt itself to perform different behaviors (Medathati NVK et al 2016).…”

Section: Facing the Challenge Of Explicit Modeling In Visual Neuroscimentioning

confidence: 99%

Foreground-background segmentation revealed during natural image viewing

Papale

Leo

Cecchetti

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

“…They showed by their implementation the reproducibility of one of the feedback actions between the brain and the eyes: the control of the position and the focus of the eyes. Recently Medathati et al [10] drew attention to the importance of those retroactions and even more of the interactions between the different computation layers in the vision process and encouraged the computer vision community to develop a new computational model of the human vision that would take them into account.…”

Section: Human Vision Biomimeticsmentioning

confidence: 99%

Dual field combination for unmanned video surveillance

et al. 2017

View full text Add to dashboard Cite

Unmanned systems used for threat detection and identification are still not efficient enough for monitoring autonomously the battlefield. The limitation on size and energy makes those systems unable to use most stateof-the-art computer vision algorithms for recognition. The bio-inspired approach based on the humans peripheral and foveal visions has been reported as a way to combine recognition performance and computational efficiency. As a low resolution camera observes a large zone and detects significant changes, a second camera focuses on each event and provides a high resolution image of it. While such biomimetic existing approaches usually separate the two vision modes according to their functionality (e.g. detection, recognition) and to their basic primitives (i.e. features, algorithms), our approach uses common structures and features for both peripheral and foveal cameras, thereby decreasing the computational load with respect to the previous approaches. The proposed approach is demonstrated using simulated data. The outcome proves particularly attractive for real time embedded systems, as the primitives (features and classifier) have already proven good performances in low power embedded systems. This first result reveals the high potential of dual views fusion technique in the context of long duration unmanned video surveillance systems. It also encourages us to go further into miming the mechanisms of the human eye. In particular, it is expected that adding a retro-action of the fovea towards the peripheral vision will further enhance the quality and efficiency of the detection process.

show abstract

Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision

Cited by 83 publications

References 295 publications

Negative results in computer vision: A perspective

Negative results in computer vision: A perspective

Foreground-background segmentation revealed during natural image viewing

Dual field combination for unmanned video surveillance

Contact Info

Product

Resources

About