Although action recognition is a widely studied field in computer vision, the recognitions of aggressive activities and crowd violence actions are comparatively less studied. Nowadays, so many surveillance cameras have been installed in the streets and there is a demand for intelligent crowd activity detection systems. A method for violence detection in videos is proposed. The primary contribution is a novel transfer learning‐based violence detector that gives promising results compared with the existing detectors. First, the optical flows of the input videos are computed via Lucas–Kanade method. Then, several 2D templates are constructed with overlapping optical flow magnitudes and orientations. These templates are supplied to a pre‐trained convolutional neural network as input and deep features of different layers are extracted. Cubic kernel support vector machine and subspace k ‐nearest neighbours classifiers are trained for prediction and the proposed method is tested with three different datasets that commonly used in violence detection studies.
18 April 2022 in Signal, Image and Video Processing
Otomatik hareket tanıma sistemlerine ihtiyaç, güvenlik kameralarının sayısındaki hızlı artıştan dolayı giderek artmaktadır. Hareket tanıma, bilgisayarlı görü alanında güncel bir araştırma alanı olmasına karşın şiddet içeren sahnelerin tespiti insan ve toplum güvenliğiyle de ilişkili olması sebebiyle büyük önem taşımaktadır. Optik akış video görüntülerindeki hareketlerin tespit ve modellenmesinde sıklıkla kullanılan bir yaklaşımdır. Bu çalışmada optik akış ve derin öğrenme kullanılarak şiddet içeren aktivitelerin tanınmasında kullanılabilecek bir yöntem önerilmiştir. Bir video serisine ait optik akış serisinin bileşenleri birleştirilerek üç kanallı bir görüntü haline getirilmiş ve önceden eğitilmiş VGG-16 evrişimsel (convolutional) sinir ağına girdi olarak verilmiştir. VGG-16 ağından elde edilen derin nitelik serileri ile bir Bi-Lstm ( Bidirectional long short term memory ) sınıflayıcısı eğitilmiştir. Önerilen yöntem literatürde yer alan iki farklı veri kümesi ile test edilmiş ve literatürde yer alan diğer yaklaşımlar ile karşılattırılabilir ve daha yüksek sınıflama başarımına sahip sonuçlar elde edilmiştir.
White matter lesions (WMLs) in the human brain are generally diagnosed by using magnetic resonance (MR) images. Doctors working on WMLs generally need to calculate the volume of lesions for each patient at regular intervals in order to observe the course of diseases and manage the treatment process. This paper introduces an unsupervised automatic approach for segmentation of WMLs in the human brain. The approach consists of skull stripping, preprocessing, and lesion detection steps. Three skull stripping methods are proposed to increase successful stripping probability on various qualities of MR image data. After preprocessing and segmenting lesions, the system applies volumetric calculation and 3D visualization of lesions. This volumetric information can be used by doctors to observe changes in the lesions against regularly scanned MR images of patients. GPU-based parallel image processing techniques are utilized on Nvidia CUDA environment in order to improve performance by 40–50 times. Therefore, the developed system saves the time of doctors by providing them a fast automatic segmentation method for WMLs.
The use of depth sensors in activity recognition is a technology that emerges in human computer interaction and motion recognition. In this study, an approach to identify single-person activities using deep learning on depth image sequences is presented. First, a 3D volumetric template is generated using skeletal information obtained from a depth video. The generated 3D volume is used for extracting features by taking images from different angles at different volumes. Actions are recognized by extracting deep features using AlexNet model [1] and Histogram of Oriented Gradients (HOG) features from these images. The proposed method has been tested with MSRAction3D [2] and UTHKinect-Action3D [2] datasets. The obtained results were comparable to similar studies in the literature.