Murugan Sankaradas NEC Labs America

Murugan Sankaradas

Senior Researcher

Integrated Systems

Posts

StreamingRAG: Real-time Contextual Retrieval and Generation Framework

Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs) on these data streams. Traditional Retrieval-Augmented Generation (RAG) systems address knowledge limitations of these models, but suffer from slow preprocessing, making them unsuitable for real-time analysis. We propose StreamingRAG, a novel RAG framework designed for streaming data. StreamingRAG constructs evolving knowledge graphs capturing scene-object-entity relationships in real-time. The knowledge graph achieves temporal-aware scene representations using MM-LLMs and enables timely responses for specific events or user queries. StreamingRAG addresses limitations in existing methods, achieving significant improvements in real-time analysis (5-6x faster throughput), contextual accuracy (through a temporal knowledge graph), and reduced resource consumption (using lightweight models by 2-3x).

Retrospective : A Dynamically Configurable Coprocessor For Convolutional Neural Networks

In 2008, parallel computing posed significant challenges due to the complexities of parallel programming and the bottlenecks associated with efficient parallel execution. Inspired by the remarkable scalability achieved by networking and storage systems in handling extensive packet traffic and persistent data respectively by leveraging best-effort service, we proposed a new and fundamentally different approach of best-effort computing.Having observed that a broad spectrum of existing and emerging computing workloads were from applications that had an inherent forgiving nature [2], [5], we proposed best effort computing. The new approach resulted in disproportionate gains in power, energy and latency, while improving performance. While contemplating the concept of best-effort computing [2], we noticed the resurgence of convolutional neural networks, which generated approximate but acceptable outcomes for numerous recognition, mining, and synthesis tasks. The lead author of this retrospective had previously conducted research on neural networks for his doctoral dissertation over a decade ago, and the reemergence of neural networks proved both surprising and exciting. Recognizing the connection between best-effort computing and convolutional neural networks, in 2008 we embarked on developing a programmable and dynamically reconfigurable convolutional neural network capable of performing best effort computing for various machine learning tasks that inherently allow for multiple acceptable answers. This combination of our thoughts on best-effort computing and the gradual evolution of convolutional neural networks (deep neural networks emerged much later) culminated in our 2010 ISCA work on dynamically reconfigurable convolutional neural networks.

AnB: Application-In-A-Box To Rapidly Deploy and Self-Optimize 5G Apps

We present Application in a Box (AnB) product concept aimed at simplifying the deployment and operation of remote 5G applications. AnB comes pre-configured with all necessary hardware and software components, including sensors like cameras, hardware and software components for a local 5G wireless network, and 5G-ready apps. Enterprises can easily download additional apps from an App Store. Setting up a 5G infrastructure and running applications on it is a significant challenge, but AnB is designed to make it fast, convenient, and easy, even for those without extensive knowledge of software, computers, wireless networks, or AI-based analytics. With AnB, customers only need to open the box, set up the sensors, turn on the 5G networking and edge computing devices, and start running their applications. Our system software automatically deploys and optimizes the pipeline of microservices in the application on a tiered computing infrastructure that includes device, edge, and cloud computing. Dynamic resource management, placement of critical tasks for low-latency response, and dynamic network bandwidth allocation for efficient 5G network usage are all automatically orchestrated. AnB offers cost savings, simplified setup and management, and increased reliability and security. We’ve implemented several real-world applications, such as collision prediction at busy traffic light intersections and remote construction site monitoring using video analytics. With AnB, deployment and optimization effort can be reduced from several months to just a few minutes. This is the first-of-its-kind approach to easing deployment effort and automating self-optimization of the application during system operation.

Elixir: A System To Enhance Data Quality For Multiple Analytics On A Video Stream

IoT sensors, especially video cameras, are ubiquitously deployed around the world to perform a variety of computer vision tasks in several verticals including retail, health- care, safety and security, transportation, manufacturing, etc. To amortize their high deployment effort and cost, it is desirable to perform multiple video analytics tasks, which we refer to as Analytical Units (AUs), off the video feed coming out of every camera. As AUs typically use deep learning-based AI/ML models, their performance depend on the quality of the input video, and recent work has shown that dynamically adjusting the camera setting exposed by popular network cameras can help improve the quality of the video feed and hence the AU accuracy, in a single AU setting. In this paper, we first show that in a multi-AU setting, changing the camera setting has disproportionate impact on different AUs performance. In particular, the optimal setting for one AU may severely degrade the performance for another AU, and further the impact on different AUs varies as the environmental condition changes. We then present Elixir, a system to enhance the video stream quality for multiple analytics on a video stream. Elixir leverages Multi-Objective Reinforcement Learning (MORL), where the RL agent caters to the objectives from different AUs and adjusts the camera setting to simultaneously enhance the performance of all AUs. To define the multiple objectives in MORL, we develop new AU-specific quality estimator values for each individual AU. We evaluate Elixir through real-world experiments on a testbed with three cameras deployed next to each other (overlooking a large enterprise parking lot) running Elixir and two baseline approaches, respectively. Elixir correctly detects 7.1% (22,068) and 5.0% (15,731) more cars, 94% (551) and 72% (478) more faces, and 670.4% (4975) and 158.6% (3507) more persons than the default-setting and time-sharing approaches, respectively. It also detects 115 license plates, far more than the time-sharing approach (7) and the default setting (0).

StreetAware: A High-Resolution Synchronized Multimodal Urban Scene Dataset

Access to high-quality data is an important barrier in the digital analysis of urban settings, including applications within computer vision and urban design. Diverse forms of data collected from sensors in areas of high activity in the urban environment, particularly at street intersections, are valuable resources for researchers interpreting the dynamics between vehicles, pedestrians, and the built environment. In this paper, we present a high-resolution audio, video, and LiDAR dataset of three urban intersections in Brooklyn, New York, totaling almost 8 unique hours. The data were collected with custom Reconfigurable Environmental Intelligence Platform (REIP) sensors that were designed with the ability to accurately synchronize multiple video and audio inputs. The resulting data are novel in that they are inclusively multimodal, multi-angular, high-resolution, and synchronized. We demonstrate four ways the data could be utilized — (1) to discover and locate occluded objects using multiple sensors and modalities, (2) to associate audio events with their respective visual representations using both video and audio modes, (3) to track the amount of each type of object in a scene over time, and (4) to measure pedestrian speed using multiple synchronized camera views. In addition to these use cases, our data are available for other researchers to carry out analyses related to applying machine learning to understanding the urban environment (in which existing datasets may be inadequate), such as pedestrian-vehicle interaction modeling and pedestrian attribute recognition. Such analyses can help inform decisions made in the context of urban sensing and smart cities, including accessibility-aware urban design and Vision Zero initiatives.

DyCo: Dynamic, Contextualized AI Models

Devices with limited computing resources use smaller AI models to achieve low-latency inferencing. However, model accuracy is typically much lower than the accuracy of a bigger model that is trained and deployed in places where the computing resources are relatively abundant. We describe DyCo, a novel system that ensures privacy of stream data and dynamically improves the accuracy of small models used in devices. Unlike knowledge distillation or federated learning, DyCo treats AI models as black boxes. DyCo uses a semi-supervised approach to leverage existing training frameworks and network model architectures to periodically train contextualized, smaller models for resource-constrained devices. DyCo uses a bigger, highly accurate model in the edge-cloud to auto-label data received from each sensor stream. Training in the edge-cloud (as opposed to the public cloud) ensures data privacy, and bespoke models for thousands of live data streams can be designed in parallel by using multiple edge-clouds. DyCo uses the auto-labeled data to periodically re-train, stream-specific, bespoke small models. To reduce the periodic training costs, DyCo uses different policies that are based on stride, accuracy, and confidence information.We evaluate our system, and the contextualized models, by using two object detection models for vehicles and people, and two datasets (a public benchmark and another real-world proprietary dataset). Our results show that DyCo increases the mAP accuracy measure of small models by an average of 16.3% (and up to 20%) for the public benchmark and an average of 19.0% (and up to 64.9%) for the real-world dataset. DyCo also decreases the training costs for contextualized models by more than an order of magnitude.

APT: Adaptive Perceptual quality based camera Tuning using reinforcement learning

Cameras are increasingly being deployed in cities, enterprises and roads world-wide to enable many applications in public safety, intelligent transportation, retail, healthcare and manufacturing. Often, after initial deployment of the cameras, the environmental conditions and the scenes around these cameras change, and our experiments show that these changes can adversely impact the accuracy of insights from video analytics. This is because the camera parameter settings, though optimal at deployment time, are not the best settings for good-quality video capture as the environmental conditions and scenes around a camera change during operation. Capturing poor-quality video adversely affects the accuracy of analytics. To mitigate the loss in accuracy of insights, we propose a novel, reinforcement-learning based system APT that dynamically, and remotely (over 5G networks), tunes the camera parameters, to ensure a high-quality video capture, which mitigates any loss in accuracy of video analytics. As a result, such tuning restores the accuracy of insights when environmental conditions or scene content change. APT uses reinforcement learning, with no-reference perceptual quality estimation as the reward function. We conducted extensive real-world experiments, where we simultaneously deployed two cameras side-by-side overlooking an enterprise parking lot (one camera only has manufacturer-suggested default setting, while the other camera is dynamically tuned by APT during operation). Our experiments demonstrated that due to dynamic tuning by APT, the analytics insights are consistently better at all times of the day: the accuracy of object detection video analytics application was improved on average by ∼ 42%. Since our reward function is independent of any analytics task, APT can be readily used for different video analytics tasks.

Enhancing Video Analytics Accuracy via Real-time Automated Camera Parameter Tuning

In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition running on remote servers critically rely on surveillance cameras to capture high-quality video streams in order to achieve high accuracy. Modern IP cameras come with a large number of camera parameters that directly affect the quality of the video stream capture. While a few of such parameters, e.g., exposure, focus, white balance are automatically adjusted by the camera internally, the remaining ones are not. We denote such camera parameters as non-automated (NAUTO) parameters. In this paper, we first show that environmental condition changes can have significant adverse effect on the accuracy of insights from the AUs, but such adverse impact can potentially be mitigated by dynamically adjusting NAUTO camera parameters in response to changes in environmental conditions. We then present CamTuner, to our knowledge, the first framework that dynamically adapts NAUTO camera parameters to optimize the accuracy of AUs in a VAP in response to adverse changes in environmental conditions. CamTuner is based on SARSA reinforcement learning and it incorporates two novel components: a light-weight analytics quality estimator and a virtual camera that drastically speed up offline RL training. Our controlled experiments and real-world VAP deployment show that compared to a VAP using the default camera setting, CamTuner enhances VAP accuracy by detecting 15.9% additional persons and 2.6%–4.2% additional cars (without any false positives) in a large enterprise parking lot and 9.7% additional cars in a 5G smart traffic intersection scenario, which enables a new usecase of accurate and reliable automatic vehicle collision prediction (AVCP). CamTuner opens doors for new ways to significantly enhance video analytics accuracy beyond incremental improvements from refining deep-learning models.

Why is the video analytics accuracy fluctuating, and what can we do about it?

It is a common practice to think of a video as a sequence of images (frames), and re-use deep neural network models that are trained only on images for similar analytics tasks on videos. In this paper, we show that this “leap of faith” that deep learning models that work well on images will also work well on videos is actually flawed. We show that even when a video camera is viewing a scene that is not changing in any human-perceptible way, and we control for external factors like video compression and environment (lighting), the accuracy of video analytics application fluctuates noticeably. These fluctuations occur because successive frames produced by the video camera may look similar visually but are perceived quite differently by the video analytics applications. We observed that the root cause for these fluctuations is the dynamic camera parameter changes that a video camera automatically makes in order to capture and produce a visually pleasing video. The camera inadvertently acts as an “unintentional adversary” because these slight changes in the image pixel values in consecutive frames, as we show, have a noticeably adverse impact on the accuracy of insights from video analytics tasks that re-use image-trained deep learning models. To address this inadvertent adversarial effect from the camera, we explore the use of transfer learning techniques to improve learning in video analytics tasks through the transfer of knowledge from learning on image analytics tasks. Our experiments with a number of different cameras, and a variety of different video analytics tasks, show that the inadvertent adversarial effect from the camera can be noticeably offset by quickly re-training the deep learning models using transfer learning. In particular, we show that our newly trained Yolov5 model reduces fluctuation in object detection across frames, which leads to better tracking of objects (∼40% fewer mistakes in tracking). Our paper also provides new directions and techniques to mitigate the camera’s adversarial effect on deep learning models used for video analytics applications.

Efficient Compression Method for Roadside LiDAR Data

Roadside LiDAR (Light Detection and Ranging) sensors are recently being explored for intelligent transportation systems aiming at safer and faster traffic management and vehicular operations. A key challenge in such systems is to efficiently transfer massive point-cloud data from the roadside LiDAR devices to the edge connected through a 5G network for real-time processing. In this paper, we consider the problem of compressing roadside (i.e. static) LiDAR data in real-time that provides a unique condition unexplored by current methods. Existing point-cloud compression methods assume moving LiDARs (that are mounted on vehicles) and do not exploit spatial consistency across frames over time.To this end, we develop a novel grouped wavelet technique for static roadside LiDAR data compression (i.e. SLiC). Our method compresses LiDAR data both spatially and temporally using a kd-tree data structure based on Haar wavelet coefficients. Experimental results show that SLiC can compress up to 1.9× more effectively than the state-of-the-art compression method can do. Moreover, SLiC is computationally more efficient to achieve 2× improvement in bandwidth usage over the best alternative. Even with this impressive gain in communication and storage efficiency, SLiC retains down-the-pipeline application’s accuracy.