TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs

Traffic cameras are essential in urban areas, playing a crucial role in intelligent transportation systems. Multiple cameras at intersections enhance law enforcement capabilities, traffic management, and pedestrian safety. However, efficiently managing and analyzing multi-camera feeds poses challenges due to the vast amount of data. Analyzing such huge video data requires advanced analytical tools. While Large Language Models (LLMs) like ChatGPT, equipped with retrieval-augmented generation (RAG) systems, excel in text-based tasks, integrating them into traffic video analysis demands converting video data into text using a Vision-Language Model (VLM), which is time-consuming and delays the timely utilization of traffic videos for generating insights and investigating incidents. To address these challenges, we propose TrafficLens, a tailored algorithm for multi-camera traffic intersections. TrafficLens employs a sequential approach, utilizing overlapping coverage areas of cameras. It iteratively applies VLMs with varying token limits, using previous outputs as prompts for subsequent cameras, enabling rapid generation of detailed textual descriptions while reducing processing time. Additionally, TrafficLens intelligently bypasses redundant VLM invocations through an object-level similarity detector. Experimental results with real-world datasets demonstrate that TrafficLens reduces video-to-text conversion time by up to 4× while maintaining information accuracy.

Accelerating Distributed Machine Learning with an Efficient AllReduce Routing Strategy

We propose an efficient routing strategy for AllReduce transfers, which compromise of the dominant traffic in machine learning-centric datacenters, to achieve fast parameter synchronization in distributed machine learning, improving the average training time by 9%.

Remote Sensing for Power Grid Fuse Tripping Using AI-Based Fiber Sensing with Aerial Telecom Cables

For the first time, we demonstrate remote sensing of pole-mounted fuse-cutout blowing in a power grid setup using telecom fiber cable. The proposed frequency-based AI model achieves over 98% detection accuracy using distributed fiber sensing data.

Measuring the Transceivers Back-to-Back BER-OSNR Characteristic Using Only a Variable Optical Attenuator

We propose a transceiver back-to-back BER-OSNR characterization method that requires only a single VOA; it leverages the receiver SNR degradation caused by received power attenuation. Experiments using commercial transceivers show that the measurement error is less than 0.2 dB in the Q-factor.

Machine Learning Model for EDFA Predicting SHB Effects

Experiments show that machine learning model of an EDFA is capable of modelling spectral hole burning effects accurately. As a result, it significantly outperforms black-box models that neglect inhomogeneous effects. Model achieves a record average RMSE of 0.0165 dB between the model predictions and measurements.

First Field Demonstration of Hollow-Core Fibre Supporting Distributed Acoustic Sensing and DWDM Transmission

We demonstrate a method for measuring the backscatter coefficient of hollow-core fibre (HCF), and show the feasibility of distributed acoustic sensing (DAS) with simultaneous 9.6-Tb/s DWDM transmission over a 1.6-km field-deployed HCF cable.

Extension of the Local-Optimization Global-Optimization (LOGO) Launch Power Strategy to Multi-Band Optical Networks

We propose extending the LOGO strategy for launch power settings to multi-band scenarios, maintaining low complexity while addressing key inter-band nonlinear effects and accurate amplifier models. This methodology simplifies multi-band optical multiplex section control, providing an immediate, descriptive estimation of optimized launch power.

NEC Labs America Team Attends the 2024 European Conference on Optical Communication (ECOC) in Frankfurt, Germany

Our optical networking & sending team has arrived in Frankfurt for the 2024 European Conference on Optical Communication (ECOC)  and is excited to present many papers and tutorials this week. Please follow this page and on our social media channels for updates.

Predicting Spatially Resolved Gene Expression via Tissue Morphology using Adaptive Spatial GNNs (ECCB)

Spatial transcriptomics technologies, which generate a spatial map of gene activity, can deepen the understanding of tissue architecture and its molecular underpinnings in health and disease. However, the high cost makes these technologies difficult to use in practice. Histological images co-registered with targeted tissues are more affordable and routinely generated in many research and clinical studies. Hence, predicting spatial gene expression from the morphological clues embedded in tissue histological images provides a scalable alternative approach to decoding tissue complexity.

OPENCAM: Lensless Optical Encryption Camera

Lensless cameras multiplex the incoming light before it is recorded by the sensor. This ability to multiplex the incoming light has led to the development of ultra-thin, high-speed, and single-shot 3D imagers. Recently, there have been various attempts at demonstrating another useful aspect of lensless cameras – their ability to preserve the privacy of a scene by capturing encrypted measurements. However, existing lensless camera designs suffer numerous inherent privacy vulnerabilities. To demonstrate this, we develop the first comprehensive attack model for encryption cameras, and propose OpEnCam – a novel lensless optical en cryption ca mera design that overcomes these vulnerabilities. OpEnCam encrypts the incoming light before capturing it using the modulating ability of optical masks. Recovery of the original scene from an OpEnCam measurement is possible only if one has access to the camera’s encryption key, defined by the unique optical elements of each camera. Our OpEnCam design introduces two major improvements over existing lensless camera designs – (a) the use of two co-axially located optical masks, one stuck to the sensor and the other a few millimeters above the sensor and (b) the design of mask patterns, which are derived heuristically from signal processing ideas. We show, through experiments, that OpEnCam is robust against a range of attack types while still maintaining the imaging capabilities of existing lensless cameras. We validate the efficacy of OpEnCam using simulated and real data. Finally, we built and tested a prototype in the lab for proof-of-concept.