A Fast Visual Search and Recognition Mechanism for Real-Time Robotics Applications

Vong, Quoc; Lozo, P.; Jain, Lakhmi C.

doi:10.1007/978-3-540-30549-1_82

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, physiological studies of the human visual system have suggested that the process of recognising objects in the scenes seems to be split into two distinctive and bidirectionally interacting stages [57][58][59]: pre-attentive and attentive. The pre-attentive stage is a fast global process which aims at identifying regions of interest (ROIs) that are most likely to have the target object embedded within them.…”

Section: Proposed Vision Systemmentioning

confidence: 99%

“…Similarly, it uses the concept of top-down facilitatory and inhibition modulation in the SAART neural network [28,29], but achieves the steady state solution much faster, thus offering real-time processing [58,63]. The architecture integrates the preattentive and attentive stages into the unique feedforward and feedbackward structures as shown in Fig.…”

Section: Visual Landmark Recognition Architecturementioning

confidence: 99%

“…2. The preattentive stage is implemented as a memory-guided search mechanism for providing rapid landmark search and detection [58]. The attentive stage, on the other hand, employs an edge-based template matching in combination with the MFM mechanism to reliably recognise visual landmarks [63].…”

Section: Visual Landmark Recognition Architecturementioning

confidence: 99%

See 2 more Smart Citations

Application of neural processing paradigm in visual landmark recognition and autonomous robot navigation

Jain

2009

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

This article addresses the issue of visual landmark recognition in autonomous robot navigation along known routes, by intuitively exploiting the functions of the human visual system and its navigational ability. A feedforward-feedbackward architecture has been developed for recognising visual landmarks in real time. It integrates the theoretical concepts from the pre-attentive and attentive stages in the human visual system, the selective attention adaptive resonance theory neural network and its derivatives, and computational approaches towards object recognition in computer vision. The architecture mimics the pre-attentive and attentive stages in the context of object recognition, embedding neural network processing paradigm into a computational template-matching approach in computer vision. The real-time landmark recognition capability is achieved by mimicking the pre-attentive stage, where it models a selective attention mechanism for optimal computational resource allocation, focusing only on the regions of interest to address the computational restrictive nature of current computer processing power. Similarly, the recognition of visual landmarks in both clean and cluttered backgrounds is implemented in the attentive stage by developing a memory feedback modulation (MFM) mechanism that enables knowledge from the memory to interact and enhance the efficiency of earlier stages in the architecture. Furthermore, it also incorporates both top-down and bottom-up facilitatory and inhibition pathways between the memory and the earlier stages to enable the architecture to recognise a 2D landmark, which is partially occluded by adjacent features in the surroundings. The results show that the architecture is able to recognise objects in cluttered backgrounds using real-images in both indoor and outdoor scenes. Furthermore, the architecture application in autonomous robot navigation has been demonstrated through a number of real-time trials in both indoor and outdoor environments.

show abstract

Section: Proposed Vision Systemmentioning

confidence: 99%

Section: Visual Landmark Recognition Architecturementioning

confidence: 99%