Department Publications

Image generation from a single image using generative adversarial networks is quite interesting due to the realism of generated images. However, recent approaches need improvement for such realistic and diverse image generation, when the global context of the image is important such as in face, animal, and architectural image generation. This is mainly due to the use of fewer convolutional layers for capturing the patch statistics and, thereby, not being able to capture global statistics well. The challenge, then, is to preserve the global structure, while retaining the diversity and quality of image generation. We solve this problem by using attention blocks at selected scales and feeding a random Gaussian blurred image to the discriminator for training. We use adversarial feedback to make the quality of the generation better. Our results are visually better than the state-of-the-art, particularly, in generating images that …

Light field saliency detection–important due to utility in many vision tasks–still lacks speed and can improve in accuracy. Due to the formulation of the saliency detection problem in light fields as a segmentation task or a memorizing task, existing approaches consume unnecessarily large amounts of computational resources for training, and have longer execution times for testing. We solve this by aggressively reducing the large light field images to a much smaller three-channel feature map appropriate for saliency detection using an RGB image saliency detector with attention mechanisms. We achieve this by introducing a novel convolutional neural network based features extraction and encoding module. Our saliency detector takes 0.4 s to process a light field of size 9× 9× 512× 375 in a CPU and is significantly faster than state-of-the-art light field saliency detectors, with better or comparable accuracy. Furthermore …

Traffic light detection is essential for self-driving cars to navigate safely in urban areas. Publicly available traffic light datasets are inadequate for the development of algorithms for detecting distant traffic lights that provide important navigation information. We introduce a novel bench-mark traffic light dataset captured using a synchronized pair of narrow-angle and wide-angle cameras covering urban and semi-urban roads. We provide 1032 images for training and 813 synchronized image pairs for testing. Additionally, we provide synchronized test video pairs for qualitative analysis. The dataset includes images of resolution covering 10 different classes. Furthermore, we propose a post-processing algorithm for combining outputs from the two cameras. Results show that our technique can strike a balance between speed and accuracy, compared to the conventional approach of using a single camera frame …

We propose a novel attention-based deep learning framework for reconstructing images from compressively sensed measurements. Our method leverages knowledge of the sampling basis and structured sampling patterns, highlighting the importance of learning adaptive features from measurements.

Class Incremental Learning (CIL) is inspired by the human ability to learn new classes without forgetting previous ones. CIL becomes more challenging in real-world scenarios when the samples in each incremental step are imbalanced. This creates another branch of problem, called Generalized Class Incremental Learning (GCIL) where each incremental step is structured more realistically. Grow When Required (GWR) network, a type of Self-Organizing Map (SOM), dynamically creates and removes nodes and edges for adaptive learning. GWR performs incremental learning from feature vectors extracted by a Convolutional Neural Network (CNN), which acts as a feature extractor. The inherent ability of GWR to form distinct clusters, each corresponding to a class in the feature vector space, regardless of the order of samples or class imbalances, is well suited to achieving GCIL. To enhance GWR's classification …

Real-time and online action localization in videos poses a critical and formidable challenge. Achieving accurate action localization necessitates the integration of both temporal and spatial information. However, existing approaches rely on computationally intensive 3D convolutional neural network (CNN) architectures or redundant two-stream architectures with optical flow, rendering them unsuitable for real-time, online applications. To address this, we propose a novel approach that leverages fast and efficient key-point-based bounding box prediction for spatial action localization. Additionally, we introduce a tube-linking algorithm that ensures the temporal continuity of action tubes even in the presence of occlusions. By combining temporal and spatial information into a cascaded input for a single network, we eliminate the need for a two-stream architecture, enabling the network to effectively learn from both types …

Law enforcement officials heavily depend on Forensic Video Analytic (FVA) Software in their evidence extraction process. However present-day FVA software are complex, time consuming, equipment dependent and expensive. Developing countries struggle to gain access to this gateway to a secure haven. The term forensic pertains the application of scientific methods to the investigation of crime through post-processing, whereas surveillance is the close monitoring of real-time feeds. The principle objective of this Final Year Project was to develop an efficient and effective FVA Software, addressing the shortcomings through a stringent and systematic review of scholarly research papers, online databases and legal documentation. The scope spans multiple object detection, multiple object tracking, anomaly detection, activity recognition, tampering detection, general and specific image enhancement and video synopsis. Methods employed include many machine learning techniques, GPU acceleration and efficient, integrated architecture development both for real-time and postprocessing. For this CNN, GMM, multithreading and OpenCV C++ coding were used. The implications of the proposed methodology would rapidly speed up the FVA process especially through the novel video synopsis research arena. This project has resulted in three research outcomes Moving Object Based Collision Free Video Synopsis, Forensic and Surveillance Analytic Tool Architecture and Tampering Detection Inter-Frame Forgery. The results include forensic and surveillance panel outcomes with emphasis on video synopsis and Sri Lankan context. Principal …

Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving. Existing trajectory-based video synopsis algorithms will not able to work in real time, because of the complexity due to the number of object tubes that need to be included in the complex energy minimization algorithm. We propose a real-time algorithm by using a method that incrementally stitches each frame of the synopsis by extracting object frames from the user specified number of tubes in the buffer in contrast to global energy-minimization based systems. This also gives flexibility to the user to set the threshold of maximum number of objects in the synopsis video according his or her tracking ability and creates collision-free summarized videos which are visually pleasing. Experiments with six common test videos, indoors and outdoors with many …

Traffic management is a serious problem in many cities around the world. Even the suburban areas are now experiencing regular traffic congestion. Inappropriate traffic control wastes fuel, time, and the productivity of nations. Though traffic signals are used to improve traffic flow, they often cause problems due to inappropriate or obsolete timing that does not tally with the actual traffic intensity at the intersection. Traffic intensity determination based on statistical methods only gives the average intensity expected at any given time. However, to control traffic accurately, it is required to know the real-time traffic intensity. In this research, image processing and machine learning have been used to estimate actual traffic intensity in real time. General-purpose electronic hardware has been used for in-situ image processing based on the edge-detection method. A deep neural network (DNN) was trained to infer traffic intensity in each image in real time. The trained DNN estimated traffic intensity accurately in 90% of the real-time images during road tests. The electronic system was implemented on a Raspberry Pi single-board computer; hence, it is cost-effective for large-scale deployment.

Compressive sensing (CS) reconstructs images from sub-Nyquist measurements by solving a sparsity-regularized inverse problem. Traditional CS solvers use iterative optimizers with hand crafted sparsifiers, while early data-driven methods directly learn an inverse mapping from the low-dimensional measurement space to the original image space. The latter outperforms the former, but is restrictive to a pre-defined measurement domain. More recent, deep unrolling methods combine traditional proximal gradient methods and data-driven approaches to iteratively refine an image approximation. To achieve higher accuracy, it has also been suggested to learn both the sampling matrix, and the choice of measurement vectors adaptively. Contrary to the current trend, in this work we hypothesize that a general inverse mapping from a random set of compressed measurements to the image domain exists for a given measurement basis, and can be learned. Such a model is single-shot, non-restrictive and does not parametrize the sampling process. To this end, we propose MOSAIC, a novel compressive sensing framework to reconstruct images given any random selection of measurements, sampled using a fixed basis. Motivated by the uneven distribution of information across measurements, MOSAIC incorporates an embedding technique to efficiently apply attention mechanisms on an encoded sequence of measurements, while dispensing the need to use unrolled deep networks. A range of experiments validate our proposed architecture as a promising alternative for existing CS reconstruction methods, by achieving the state-of-the-art for metrics of …

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which operates without any human labeling, is a promising approach to address this issue. We observe in the real world that humans are capable of mapping the visual concepts learnt from 2D images to understand the 3D world. Encouraged by this insight, we propose CrossPoint, a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representations. It enables a 3D-2D correspondence of objects by maximizing agreement between point clouds and the corresponding rendered 2D image in the invariant space, while encouraging invariance to transformations in the point cloud modality. Our joint training objective combines the feature correspondences within and …

In this paper, we introduce a novel road marking bench-mark dataset for road marking detection, addressing the limitations in the existing publicly available datasets such as lack of challenging scenarios, prominence given to lane markings, unavailability of an evaluation script, lack of an-notation formats and lower resolutions. Our dataset consists of 2887 total images with 4706 road marking instances belonging to 11 classes. The images have a high resolution of 1920 × 1080 and capture a wide range of traffic, lighting and weather conditions. We provide road marking an-notations in polygons, bounding boxes and pixel-level segmentation masks to facilitate a diverse range of road marking detection algorithms. The evaluation metrics and the evaluation script we provide, will further promote direct comparison of novel approaches for road marking detection with existing methods. Furthermore, we evaluate the …

Recent work done on traffic sign and traffic light detection focus on improving detection accuracy in complex scenarios, yet many fail to deliver real-time performance, specifically with limited computational resources. In this work, we propose a simple deep learning based end-to-end detection framework, which effectively tackles challenges inherent to traffic sign and traffic light detection such as small size, large number of classes and complex road scenarios. We optimize the detection models using TensorRT and integrate with Robot Operating System to deploy on an Nvidia Jetson AGX Xavier as our embedded device. The overall system achieves a high inference speed of 63 frames per second, demonstrating the capability of our system to perform in real-time. Furthermore, we introduce CeyRo, which is the first ever large-scale traffic sign and traffic light detection dataset for the Sri Lankan context. Our dataset …

Human behavioral monitoring during sleep is essential for various medical applications. Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions. Long-wavelength infrared (LWIR) modality based pose estimation algorithms overcome the aforementioned challenges; however, ground truth pose generations by a human annotator under such conditions are not feasible. A feasible solution to address this issue is to transfer the knowledge learned from images with pose labels and no occlusions, and adapt it towards real world conditions (occlusions due to blankets). In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in …

Few-Shot learning aims to train and optimize a model that can adapt to unseen visual classes with only a few labeled examples. The existing few-shot learning (FSL) methods, heavily rely only on visual data, thus fail to capture the semantic attributes to learn a more generalized version of the visual concept from very few examples. However, it is a known fact that human visual learning benefits immensely from inputs from multiple modalities such as vision, language, and audio. Inspired by the human learning nature of encapsulating the existing knowledge of a visual category which is in the form of language, we introduce a contrastive alignment mechanism for visual and semantic feature vectors to learn much more generalized visual concepts for few-shot learning. Our method simply adds an auxiliary contrastive learning objective which captures the contextual knowledge of a visual category from a strong textual encoder in addition to the existing training mechanism. Hence, the approach is more generalized and can be plugged into any existing FSL method. The pre-trained semantic feature extractor (learned from a large-scale text corpora) we use in our approach provides a strong contextual prior knowledge to assist FSL. The experimental results done in popular FSL datasets show that our approach is generic in nature and provides a strong boost to the existing FSL baselines.

Raw point cloud processing using capsule networks is widely adopted in classification, reconstruction, and segmentation due to its ability to preserve spatial agreement of the input data. However, most of the existing capsule based network approaches are computationally heavy and fail at representing the entire point cloud as a single capsule. We address these limitations in existing capsule network based approaches by proposing PointCaps, a novel convolutional capsule architecture with parameter sharing. Along with PointCaps, we propose a novel Euclidean distance routing algorithm and a class-independent latent representation. The latent representation captures physically interpretable geometric parameters of the point cloud, with dynamic Euclidean routing, PointCaps well-represents the spatial (point-to-part) relationships of points. PointCaps has a significantly lower number of parameters and requires a …

Indoor cycling is a concept that has emerged with technological advancements to serve multiple purposes such as fitness, virtual tourism, and leisure. Commercial solutions have been developed to serve different user groups, with emphasis on corresponding aspects of user experience. This paper proposes a novel approach to indoor cycling, combining key features including real-world 360-degree view, immersive environment, real-time interaction between the real and virtual worlds and dynamic resistance control to simulate changes in elevation. In the proposed solution, a mobile application provides an immersive cycling environment by playing 360-degree videos on a Virtual Reality headset. The environment responds to user movements such as head rotation and cycling speed changes, and in return replicates the actual resistance to the rider using automatic resistance control. These components are …

Inspired by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing and feature learning over large-scale outdoor LiDAR point clouds. We observe that existing GNN based methods fail to overcome challenges of scale and irregularity of points in outdoor datasets. Addressing the need to preserve structural details while learning over a larger volume efficiently, we propose Hierarchical Point Graph Neural Network (HPGNN). It learns node features at various levels of graph coarseness to extract information. This enables to learn over a large point cloud while retaining fine details that existing pointlevel graph networks struggle to achieve. Connections between multiple levels enable a point to learn features in multiple scales, in a few iterations. We design HPGNN as a purely GNN-based approach, so that it offers modular …

Many of the existing Person Re-identification (Re-ID) approaches depend on feature maps which are either partitioned to localize parts of a person or reduced to create a global representation. While part localization has shown significant success, it uses either na{\i}ve position-based partitions or static feature templates. These, however, hypothesize the pre-existence of the parts in a given image or their positions, ignoring the input image-specific information which limits their usability in challenging scenarios such as Re-ID with partial occlusions and partial probe images. In this paper, we introduce a spatial attention-based Dynamic Part Template Initialization module that dynamically generates part-templates using mid-level semantic features at the earlier layers of the backbone. Following a self-attention layer, human part-level features of the backbone are used to extract the templates of diverse human body parts using a simplified cross-attention scheme which will then be used to identify and collate representations of various human parts from semantically rich features, increasing the discriminative ability of the entire model. We further explore adaptive weighting of part descriptors to quantify the absence or occlusion of local attributes and suppress the contribution of the corresponding part descriptors to the matching criteria. Extensive experiments on holistic, occluded, and partial Re-ID task benchmarks demonstrate that our proposed architecture is able to achieve competitive performance. Codes will be included in the supplementary material and will be made publicly available.

We present an end-to-end virtual try-on pipeline, that can fit different clothes on a personalized 3-D human model, reconstructed using a single RGB image. Our main idea is to construct an animatable 3-D human model and try-on different clothes in a 3-D virtual environment. The existing frame by frame volumetric reconstruction of 3-D human models are highly resource-demanding and do not allow clothes switching. Moreover, existing virtual fit-on systems also lack realism due to predominantly being 2-D or not using user's features in the reconstruction. These shortcomings are due to either the human body or clothing model being 2-D or not having the user's facial features in the dressed model. We solve these problems by manipulating a parametric representation of the 3-D human body model and stitching a head model reconstructed from the actual image. Fitting the 3-D clothing models on the parameterized human model is also adjustable to the body shape of the input image. Our reconstruction results, in comparison with recent existing work, are more visually-pleasing.

3D generative models have been recently successful in generating realistic 3D objects in the form of point clouds. However, most models do not offer controllability to manipulate the shape semantics of component object parts without extensive semantic attribute labels or other reference point clouds. Moreover, beyond the ability to perform simple latent vector arithmetic or interpolations, there is a lack of understanding of how part-level semantics of 3D shapes are encoded in their corresponding generative latent spaces. In this paper, we propose 3DLatNav; a novel approach to navigating pretrained generative latent spaces to enable controlled part-level semantic manipulation of 3D objects. First, we propose a part-level weakly-supervised shape semantics identification mechanism using latent representations of 3D shapes. Then, we transfer that knowledge to a pretrained 3D object generative latent space to unravel disentangled embeddings to represent different shape semantics of component parts of an object in the form of linear subspaces, despite the unavailability of part-level labels during the training. Finally, we utilize those identified subspaces to show that controllable 3D object part manipulation can be achieved by applying the proposed framework to any pretrained 3D generative model. With two novel quantitative metrics to evaluate the consistency and localization accuracy of part-level manipulations, we show that 3DLatNav outperforms existing unsupervised latent disentanglement methods in identifying latent directions that encode part-level shape semantics of 3D objects. With multiple ablation studies and testing on state-of-the …

Drones can be very useful in search and rescue missions primarily due to the aerial imaging capability. Drones can assist ground teams searching for a missing person, and law enforcement officers in crowd control. But there are instances where the observer on the ground control station misses the subtle information on the video feed coming from the drone. In fact, it is a very difficult job for the observer to be so vigilant in viewing a lot of images looking for a sign of a human in those images. This paper presents a drone-based human identification system to make search and rescue missions more effective. The drone, once detects signs of human presence in real-time aerial videos, autonomously navigates towards the suspicious location to get a better view to verify human presence. The drone has been made fully autonomous with operator override as an option. It processes images and sends selected frames for …

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years. However, this comes at the cost of heavy computation and memory intensive network designs, suggesting potential improvements in efficiency. Convolutional layers of CNNs partly account for such an inefficiency, as they are known to learn redundant features. In this work, we exploit this redundancy, observing it as the correlation between convolutional filters of a layer, and propose an alternative approach to reproduce it efficiently. The proposed `LinearConv' layer learns a set of orthogonal filters, and a set of coefficients that linearly combines them to introduce a controlled redundancy. We introduce a correlation-based regularization loss to achieve such flexibility over redundancy, and control the number of parameters in turn. This is designed as a plug-and-play layer to conveniently …

Recent work done on lane detection has been able to detect lanes accurately in complex scenarios, yet many fail to deliver real-time performance specifically with limited computational resources. In this work, we propose SwiftLane: a simple and light-weight, end-to-end deep learning based framework, coupled with the row-wise classification formulation for fast and efficient lane detection. This framework is supplemented with a false positive suppression algorithm and a curve fitting technique to further increase the accuracy. Our method achieves an inference speed of 411 frames per second, surpassing state-of the-art in terms of speed while achieving comparable results in terms of accuracy on the popular CULane benchmark dataset. In addition, our proposed framework together with TensorRT optimization facilitates real-time lane detection on a Nvidia Jetson AGX Xavier as an embedded system while achieving …