Design and implementation of colour texture-basedmultiple object detection usingmorphological gradient approach

摘要

Non-rigid moving multiple objects detection and tracking play an important role in intelligentvideo surveillance system, autonomous navigation, and activity analysis.Closed Circuit Television(CCTV) systems are deployed in numerous areas such as airports, traffic intersections, undergroundstations,mass events, mall, schools, and organisations for security and public surveillance.Although these cameras record continuous video 24×7, it is a human constraint to manually monitorall events such as crime, terrorism, hideous, suspicious activities, the positioning of the vehicle,and fire recorded from a number of cameras. Moreover, problems like dynamic background, thecreation of ghost, sensor noise, varying illumination, and colour and compression artefacts affecteffective detection of multiple moving objects. This study presents an effective approach namedas enhanced Fractal Texture Analysis with KNN classifier (FTAKC) for tracking and detection ofmultiple objects from a video sequence. The proposed approach comprises three main phases,namely, detection ofmoving object, tracking of the object (enhanced Fractal Texture Analysis), andbehaviour analysis for activity recognition (KNNclassifier). The image feature has been extractedbased on colour, texture, and geometry were used to identify and track multiple objects in videoframes, and Problem domain knowledge rules were applied to distinguish normal or anomalousactivities aswell asbehaviours.Edgedetection algorithm (Intersection overUnion (IoU) thresholdto determine possible edge connections)was applied toward enhancing the illumination variationby multi-block Local Binary Pattern (LBP) temporal-analysis to do the segmentation. Finally, theefficiency and effectiveness of the proposed approach has been estimated based on the measureof average PSNR, precision, recall, f-measure, accuracy, and execution time. The Laboratory forImage and Media Understanding (LIMU) dataset has been utilised toward illustrating the robustnessof the proposed approach. Furthermore, it evaluated the performance based on the measureof precision, recall, and F-measure metrics. It has been tentatively demonstrated that the proposedapproach is suitable for recognizing multiple moving object with detection accuracy up to93.56%. The simulated results show that suggested approach is robust, flexible, as well as able tooutperform the traditional methods than the present object detection method.