Department Publications

We present a MUSIC-based Direction of Arrival (DOA) estimation strategy using small antenna arrays, via employing deep learning for reconstructing the signals of a virtual large antenna array. Not only does the proposed strategy deliver significantly better performance than simply plugging the incoming signals into MUSIC, but surprisingly, the performance is also better than directly using an actual large antenna array with MUSIC for high angle ranges and low test SNR values. We further analyze the best choice for the training SNR as a function of the test SNR, and observe dramatic changes in the behavior of this function for different angle ranges.

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 …

Learning a particular task from a dataset, samples in which originate from diverse contexts, is challenging, and usually addressed by deepening or widening standard neural networks. As opposed to conventional network widening, multipath architectures restrict the quadratic increment of complexity to a linear scale. However, existing multi-column/path networks or model ensembling methods do not consider any feature-dependent allocation of parallel resources, and therefore, tend to learn redundant features. Given a layer in a multi-path network, if we restrict each path to learn a context-specific set of features and introduce a mechanism to intelligently allocate incoming feature maps to such paths, each path can specialize in a certain context, reducing the redundancy and improving the quality of extracted features. This eventually leads to better-optimized usage of parallel resources. To do this, we propose …

Real-time and online action localization in a video is a critical yet highly challenging problem. Accurate action localization requires the utilization of both temporal and spatial information. Recent attempts achieve this by using computationally intensive 3D CNN architectures or highly redundant two-stream architectures with optical flow, making them both unsuitable for real-time, online applications. To accomplish activity localization under highly challenging real-time constraints, we propose utilizing fast and efficient key-point based bounding box prediction to spatially localize actions. We then introduce a tube-linking algorithm that maintains the continuity of action tubes temporally in the presence of occlusions. Further, we eliminate the need for a two-stream architecture by combining temporal and spatial information into a cascaded input to a single network, allowing the network to learn from both types of information. Temporal information is efficiently extracted using a structural similarity index map as opposed to computationally intensive optical flow. Despite the simplicity of our approach, our lightweight end-to-end architecture achieves state-of-the-art frame-mAP of 74.7% on the challenging UCF101-24 dataset, demonstrating a performance gain of 6.4% over the previous best online methods. We also achieve state-of-the-art video-mAP results compared to both online and offline methods. Moreover, our model achieves a frame rate of 41.8 FPS, which is a 10.7% improvement over contemporary real-time methods.

Self-localization based on passive RFID-based has many potential applications. One of the main challenges it faces is the suppression of the reflected signals from unwanted objects (i.e., clutter). Typically, the clutter echoes are much stronger than the backscattered signals of the passive tag landmarks used in such scenarios. Therefore, successful tag detection can be very challenging. We consider two types of tags, namely low-Q and high-Q tags. The high-Q tag features a sparse frequency response, whereas the low-Q tag presents a broad frequency response. Further, the clutter usually showcases a short-lived response. In this work, we propose an iterative algorithm based on a low-rank plus sparse recovery approach (RPCA) to mitigate clutter and retrieve the landmark response. In addition to that, we compare the proposed approach with the well-known time-gating technique. It turns out that RPCA outperforms significantly time-gating for low-Q tags, achieving clutter suppression and tag identification when clutter encroaches on the time-gating window span, whereas it also increases the backscattered power at resonance by approximately 12 dB at 80 cm for high-Q tags. Altogether, RPCA seems a promising approach to improve the identification of passive indoor self-localization tag landmarks.

Defect detection plays an important role in product quality assurance in many industrial applications. Air-coupled ultrasound defect detection setups have the advantage that they are non-destructive and do not contaminate the investigated materials. However, this approach comes with some challenges due to the weak signaling response of the defects. Thus, sophisticated signal separation methods are required. To address this challenge, low-rank-plus-sparse recovery (LRPSR) is proposed and compared with state-of-the-art machine learning (ML) methods. The results obtained show that the LRPSR method achieves comparable results in terms of detection rate to those achieved by ML. Yet, for a small training data set, the LRPSR approach outperforms the ML algorithms. The small training data set is important for detecting defects of different production lines without having a time-consuming training process. In …

Deep neural networks (DNNs) have been successfully employed in a multitude of applications with remarkable performance. As such performance is achieved at a significant computational cost, several embedded applications demand fast and efficient hardware accelerators for DNNs. Previously proposed application specific integrated circuit (ASIC) architectures strive to utilize arrays of hundreds of processing elements (PEs) and reduce power-hungry DRAM accesses using multiple dataflows requiring complex PE architectures. These consume significant area and reduce the maximum clock frequency. This paper introduces the Kraken architecture, which optimally processes the convolutional layers, fully-connected layers, and matrix products of any DNN through a hardware-friendly uniform dataflow. This enables maximal data reuse of weights, inputs, and outputs, with a bare-bones PE design and on-the-fly dynamic reconfiguration. Kraken, implemented in 65-nm CMOS technology at 400 MHz, packs 672 PEs in 7.3 mm2, with a peak performance of 537.6 Gops. Kraken processes the convolutional layers of AlexNet, VGG-16, and ResNet-50 at 336.6, 17.5, and 64.2 frames/s, respectively, hence outperforming the state-of-the-art ASIC architectures in terms of overall performance efficiency, DRAM accesses, arithmetic intensity, and throughput, with 5.8x more Gops/mm2 and 1.6x more Gops/W.

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 mainly capturing the patch statistics and, thereby, not being able to capture global statistics very well. We solve this problem by using attention blocks at selected scales and feeding a random Gaussian blurred image to the discriminator for training. Our results are visually better than the state-of-the-art particularly in generating images that require global context. The diversity of our image generation, measured using the average standard deviation of pixels, is also better.

Large-batch training of deep neural networks (DNN) has recently been widely studied, since traversing the optimization landscape is faster with large batches and the emergence of parallel computing has made large-batch training feasible. However, its generalization is still worse compared to small-batch training, which is commonly attributed to the low gradient variance with large batches. We show that sign stochastic gradient descent (signSGD) is a suitable candidate for large-batch ResNet training with improved generalization compared to vanilla SGD. We further modify signSGD to improve the convergence for large batches while retaining its generalization properties. In particular, we propose r-signSGD, which restricts certain parameter updates of signSGD—r-signSGD updates a parameter of the neural network only if its gradient sign matches its gradient momentum sign. This prevents unnecessary/wrong …

Growing concerns over privacy invasion due to video camera based monitoring systems have made way to non-invasive Wi-Fi signal sensing based alternatives. This paper introduces a novel end-to-end deep learning framework that utilizes the changes in orthogonal frequency division multiplexing (OFDM) sub-carrier amplitude information to simultaneously predict the identity, activity and the trajectory of a user and create a user profile that is of similar utility to a one made through a video camera based approach. The novelty of the proposed solution is that the system is fully autonomous and requires zero user intervention unlike systems that require user originated initialization, or a user held transmitting device to facilitate the prediction. Experimental results demonstrate over 95% accuracy for user identification and activity recognition, while the user localization results exhibit a ±12cm error, which is a significant …

We propose self-supervised deep algorithms to detect anomalies in heterogeneous autonomous systems using frontal camera video and IMU readings. Given that the video and IMU data are not synchronized, each of them are analyzed separately. The vision-based system, which utilizes a conditional GAN, analyzes immediate-past three frames and attempts to predict the next frame. The frame is classified as either an anomalous case or a normal case based on the degree of difference estimated using the prediction error and a threshold. The IMU-based system utilizes two approaches to classify the timestamps; the first being an LSTM autoencoder which reconstructs three consecutive IMU vectors and the second being an LSTM forecaster which is utilized to predict the next vector using the previous three IMU vectors. Based on the reconstruction error, the prediction error, and a threshold, the timestamp is classified as either an anomalous case or a normal case. The composition of algorithms won runners up at the IEEE Signal Processing Cup anomaly detection challenge 2020. In the competition dataset of camera frames consisting of both normal and anomalous cases, we achieve a test accuracy of 94% and an F1-score of 0.95. Furthermore, we achieve an accuracy of 100% on a test set containing normal IMU data, and an F1-score of 0.98 on the test set of abnormal IMU data.

In this paper, we propose a novel algorithm based on supervised learning for antenna array extrapolation for the purpose of super resolution DoA estimation. We use multiple signal classification (MUSIC) as a DoA estimation technique to estimate the DoA. In order to reduce the computational burden, existing approaches focus on interpolating the missing elements in a virtual array using a sparse array (or non-uniform linear arrays) or employ antenna selection within the same aperture. In contrast, here we utilize an uniform linear array (ULA) using a low number of antennas (within a small array aperture) to extrapolate another ULA with a higher number of antennas (within a bigger aperture). This approach is not restricted to any specific antenna array configuration, in fact it can be generalized to any array configuration. We propose an algorithm which utilizes the advances of supervised learning (dictionary learning …

A combined approach of low-complexity light field depth filtering and deep learning is proposed for object classification in the presence of partial occlusions. The proposed approach exploits depth information embedded in multi-perspective four-dimensional (4-D) light fields via low-complexity 4-D sparse depth filtering and deep-learning. The proposed 4-D depth filter, designed using numerical optimization techniques by formulating as an ℓ 1 - ℓ ∞ minimization problem, is shown to outperform typical light field refocusing based on 4-D shift-sum averaging filters. Experiments conducted using a light field dataset acquired by a Lytro camera verify 45% and 27% better performance in terms of object classification accuracy compared to the cases when no depth filtering is employed and standard shift-sum refocusing is employed, respectively.

Reinforcement learning algorithms have been successfully trained for games like GO, Atari, and Chess in simulated environments. However, in cue sport-based games like Carrom, real world is unpredictable unlike in Chess and GO due to the stochastic nature of the gameplay as well as the effect of external factors such as friction combined with multiple collisions. Hence, solely training in a simulated platform for games like Billiard and Carrom, which need precise execution of a shot, would not be ideal in actual gameplay. This paper presents a real-time vision based efficient robotic system to play Carrom against a proficient human opponent. We demonstrate the challenges of adopting a reinforcement learning algorithm beyond simulations in implementing a strategic gameplay for the robotic system. We currently achieve an overall shot accuracy of 70.6% by combining heuristic and reinforcement learning …

Light field saliency detection—important due to utility in many vision tasks—still lack 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” tasks, existing approaches consume unnecessarily large amounts of computational resources for (training and) testing leading to execution times is several seconds. 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. 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 existing systems, with better or comparable accuracy. Our work shows that extracting features from light fields through aggressive size reduction and the attention results in a faster and accurate light-field saliency detector.

Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data. Drawing intuition from the success achieved by Convolutional Neural Networks (CNNs) by going deeper, we introduce DeepCaps, a deep capsule network architecture which uses a novel 3D convolution based dynamic routing algorithm. With DeepCaps, we surpass the state-of-the-art capsule domain networks results on CIFAR10, SVHN and Fashion MNIST, while achieving a 68% reduction in the number of parameters. Further, we propose a class independent decoder network, which strengthens the use of reconstruction loss as a regularization term. This leads to an interesting property of the decoder, which allows us to identify and control the physical attributes of the images represented by the instantiation parameters.

Accurately estimating the remaining useful life (RUL) of industrial machinery is beneficial in many real-world applications. Estimation techniques have mainly utilized linear models or neural network based approaches with a focus on short term time dependencies. This paper, introduces a system model that incorporates temporal convolutions with both long term and short term time dependencies. The proposed network learns salient features and complex temporal variations in sensor values, and predicts the RUL. A data augmentation method is used for increased accuracy. The proposed method is compared with several state-of-the-art algorithms on publicly available datasets. It demonstrates promising results, with superior results for datasets obtained from complex environments.

Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of labeled data for such languages and inability of deep learning techniques to properly learn from small number of training samples. We solve this problem by introducing a technique of generating new training samples from the existing samples, with realistic augmentations which reflect actual variations that are present in human hand writing, by adding random controlled noise to their corresponding instantiation parameters. Our results with a mere 200 training samples per class surpass existing character recognition results in the EMNIST-letter dataset while achieving the existing results in the three datasets: EMNIST-balanced, EMNIST-digits, and MNIST. We also develop a strategy to …

Activity recognition in videos in a deep-learning setting-or otherwise-uses both static and pre-computed motion components. The method of combining the two components, while keeping the burden on the deep network less, still remains uninvestigated. Moreover, it is not clear what the level of contribution of individual components is, and how to control the contribution. In this paper, we use a combination of convolutional-neural-network-generated static features and motion features in the form of motion tubes. We propose three schemas for combining static and motion components: based on a variance ratio, principal components, and Cholesky decomposition. The Cholesky-decomposition-based method allows the control of contributions. The ratio given by variance analysis of static and motion features matches well with the experimental optimal ratio used in the Cholesky decomposition-based method. The …

In this paper, we are concerned with indoor localization based on multiple-antenna channel measurements. Indoor localization is an active area of research due to its great importance in many applications. We propose a hybrid algorithm which combines the benefits of two techniques, namely signal processing and machine learning. We validate our algorithm based on real measurements acquired from two practical setups. Our approach shows a very promising performance in the IEEE CTW 2019 - Positioning Algorithm Competition where the algorithm achieves an accuracy within RMSE values below 10 cm. We further build a setup in another indoor environment, where the algorithm still proves a very good performance compared to state-of-the art techniques used in indoor localization tasks.

Humanoid robots that act as human-robot interfaces equipped with social skills can assist people in many of their daily activities. Receptionist robots are one such application where social skills and appearance are of utmost importance. Many existing robot receptionist systems suffer from high cost and they do not disclose internal architectures for further development for robot researchers. Moreover, there does not exist customizable open-source robot receptionist frameworks to be deployed for any given application. In this paper we present an open-source robot receptionist intelligence core-“DEVI”, that provides researchers with ease of creating customized robot receptionists according to the requirements (cost, external appearance, and required processing power). Moreover, this paper also presents details on a prototype implementation of a physical robot using the DEVI system. The robot can give directional …

Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal. No work tries to address automatic occlusion detection and removal as a context-aware generic problem. In this paper, we present a novel methodology to identify objects that do not relate to the image context as occlusions and remove them, reconstructing the space occupied coherently. The proposed system detects occlusions by considering the relation between foreground and background object classes represented as vector embeddings, and removes them through inpainting. We test our system on COCO-Stuff dataset and conduct a user study to establish a baseline in context-aware automatic occlusion removal.