Pranam Janney

Learn More
Large amounts of available training data and increasing computing power have led to the recent success of deep convolutional neural networks (CNN) on a large number of applications. In this paper, we propose an effective semantic pixel labelling using CNN features, hand-crafted features and Conditional Random Fields (CRFs). Both CNN and hand-crafted(More)
Content-Based Image Retrieval has been a major area of research in recent years. Efficient image retrieval with high precision would require an approach which combines usage of both the color and texture features of the image. In this paper we propose a method for enhancing the capabilities of texture based feature extraction and further demonstrate the use(More)
CCTV cameras are becoming a common fixture at the roadside. Their use varies from traffic monitoring to security surveillance. In this paper an advanced two-stage framework for estimating vehicular traffic density on a road segment is presented. The proposed approach is computationally efficient and robust to varying illumination. The method is novel(More)
In this paper, we present a new rotation-invariant texture descriptor algorithm called invariant features of local textures (IFLT). The proposed algorithm extracts rotation invariant features from a small neighbourhood of pixels around a centre pixel or a texture patch. Intensity vector which is derived from a texture patch is normalized and Haar wavelet(More)
The persistent airborne surveillance of large geographical areas is now a viable proposition. As well as providing cues to moving objects, it presents new opportunities for understanding the behaviours and motivations of people, both individually and collectively. Exploitation of these huge collections of imagery (a facet of the Big Data challenge) requires(More)
This work addresses the problem of extracting semantics associated with multiple, cooperatively managed motion imagery sensors to support indexing and search of large imagery collections. The extracted semantics relate to the motion and identity of vehicles within a scene, viewed from aircraft and the ground. Semantic extraction required three steps: Video(More)
In digital airborne electro-optical imagery, the identification of objects, particularly vehicles, has an important role in wide-area search and surveillance applications. We propose an identification and pose estimation approach based on maximising the correlation of features in an image with projections of 3D models. It has been applied to imagery(More)
Human tracking in crowded scenes is a challenging problem because of frequent occlusion and presence of the tracking in similar regions. In this paper, we propose an online human tracking method which can handle occlusion and targets with similar regions. Our method compares the target region with a surrounding region and targets with similar regions at(More)