IEEE Transactions on Pattern Analysis and Machine Intelligence · 2007 · 525 citations · 43 references
ComputingComputer ScienceRobotics EngineeringComputer VisionMobile RoboticsVisual AttentionFeature DescriptionImage ClassificationPattern RecognitionRobotic VisionScene ClassificationScene UnderstandingClassification AccuracyClassification Accuracy AnalysisClassification Accuracy AssessmentComputational Complexity Of AlgorithmsMultiscale SegmentationOutdoor Scene ClassificationVisual Attention For Scene Classification
We describe and validate a simple context-based scene recognition algorithm for mobile robotics applications. The system can differentiate outdoor scenes from various sites on a college campus using a multiscale set of early-visual features, which capture the "gist" of the scene into a low-dimensional signature vector. Distinct from previous approaches, the algorithm presents the advantage of being biologically plausible and of having low-computational complexity, sharing its low-level features with a model for visual attention that may operate concurrently on a robot. We compare classification accuracy using scenes filmed at three outdoor sites on campus (13,965 to 34,711 frames per site). Dividing each site into nine segments, we obtain segment classification rates between 84.21 percent and 88.62 percent. Combining scenes from all sites (75,073 frames in total) yields 86.45 percent correct classification, demonstrating the generalization and scalability of the approach.
43
A feature-integration theory of attention
Anne Treisman, Garry A. Gelade · Cognitive Psychology · 1980 · 12.4K citations
Medicine, Psychology, Vision Science +12