Sensor array and camera fusion via unbalanced optimal transport for 3D source localization
arXiv:2603.29940v1 Announce Type: new Abstract: We address the problem of localizing multiple sources in 3D by combining sensor array measurements with camera observations. We propose a fusion framework extending the covariance matrix fitting method with an unbalanced optimal transport regularization term that softly aligns sensor array responses with visual priors while allowing flexibility in mass allocation. To solve the resulting largescale problem, we adopt a greedy coordinate descent algorithm that efficiently updates the transport plan. Its computational efficiency makes full 3D localization feasible in practice. The proposed framework is modular and does not rely on labeled data or training, in contrast with deep learning-based fusion approaches. Although validated here on acoustic
View PDF
Abstract:We address the problem of localizing multiple sources in 3D by combining sensor array measurements with camera observations. We propose a fusion framework extending the covariance matrix fitting method with an unbalanced optimal transport regularization term that softly aligns sensor array responses with visual priors while allowing flexibility in mass allocation. To solve the resulting largescale problem, we adopt a greedy coordinate descent algorithm that efficiently updates the transport plan. Its computational efficiency makes full 3D localization feasible in practice. The proposed framework is modular and does not rely on labeled data or training, in contrast with deep learning-based fusion approaches. Although validated here on acoustic arrays, the method is general to arbitrary sensor arrays. Experiments on real data show that the proposed approach improves localization accuracy compared to sensor-only baselines.
Subjects:
Signal Processing (eess.SP)
Cite as: arXiv:2603.29940 [eess.SP]
(or arXiv:2603.29940v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2603.29940
arXiv-issued DOI via DataCite (pending registration)
Journal reference: IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2026, Barcelona, Spain
Submission history
From: Ilyes Jaouedi [view email] [via CCSD proxy] [v1] Tue, 31 Mar 2026 16:14:59 UTC (2,622 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
trainingannounceupdate
Mercor AI Data Breach: Supply Chain Attack via LiteLLM Package Compromise
The Mercor AI Data Breach: A Case Study in Supply Chain Vulnerability On March 24, 2026, Mercor AI, an AI-driven interview platform, suffered a significant data breach orchestrated by the hacking group Lapsus$. The attack exploited a compromised version of the LiteLLM package , a third-party language model library integrated into Mercor’s AI systems. This breach exposed approximately 4TB of sensitive data , including 211GB of candidate records , 939GB of source code , and 3TB of video interviews and identity documents . This incident starkly illustrates the systemic risks inherent in AI supply chains, where a single compromised component can trigger cascading failures, leading to massive data exposure and reputational damage. The Compromised LiteLLM Package: A Supply Chain Trojan The breac
Digital Marketing Course in Delhi: A Practical Skill Stack for High-Growth Careers in 2026
Most people think digital marketing is just about posting on social media or running ads. But in reality, it’s a data-driven, performance-based system that combines: Analytics Psychology Technology Strategy And if you're serious about building a career in this field, understanding the full ecosystem is critical. To get a structured breakdown of how these skills are actually taught and applied, you can explore this Digital Marketing Course in Delhi that focuses on real-world execution. The Shift: From Degree-Based to Skill-Based Careers The job market is changing fast. Traditional degrees alone are no longer enough. Companies are now looking for: Problem solvers Execution-focused professionals People who can generate measurable results This is where digital marketing stands out. Everything
How I Built a Desktop AI App with Tauri v2 + React 19 in 2026
I wanted to build one app that does AI chat, image generation, and video generation — all running locally, no cloud, no Docker, no terminal. Just a .exe you download and run. The result is Locally Uncensored — a React 19 + TypeScript frontend with a Tauri v2 Rust backend that connects to Ollama for chat and ComfyUI for image/video generation. It ships as a standalone desktop app on Windows (.exe/.msi), Linux (.AppImage/.deb), and macOS (.dmg). This post covers the real technical challenges I hit and how I solved them. If you're building a Tauri app that talks to local services, manages large file downloads, or needs to auto-discover software on the user's machine, this is for you. The Stack Frontend : React 19, TypeScript, Tailwind CSS 4, Framer Motion, Zustand Desktop Shell : Tauri v2 (Ru
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Releases
The All-in-One Local AI App: Chat + Images + Video Without the Cloud
There's a point in every local AI enthusiast's journey where you realize you're juggling too many tools. Ollama for chat. ComfyUI for images (if you can get it working). Some other tool for video. A separate app for voice transcription. And none of them talk to each other. You end up with five terminal windows, three browser tabs, and a growing suspicion that this shouldn't be this hard. That's why I built Locally Uncensored — a single desktop app that does AI chat, image generation, and video creation. Everything runs on your machine. Nothing touches the cloud. No Docker required. You download a .exe, double-click it, and you're done. The Problem: Death by a Thousand Tabs If you're running local AI today, your workflow probably looks something like this: Open a terminal, run ollama serve
Claude Code Just Fixed Terminal Flickering (How to Enable NO_FLICKER Mode)
The old renderer redraws the entire screen on every update, causing visible flickering NO_FLICKER mode uses a virtual viewport that only patches changed characters Enable it with CLAUDE_CODE_NO_FLICKER=1 claude or add export to .zshrc Bonus: mouse support, cleaner copy-paste, lower CPU on long sessions Still experimental but most Anthropic internal users already prefer it The Flickering Problem If you use Claude Code daily, you know this one. You ask a question, the response starts streaming, and your terminal screen starts flashing. Every new token triggers a full redraw. The longer the response, the worse it gets. Not a bug in your terminal emulator. Just how the default renderer works. Claude Code clears the screen and repaints everything from scratch on every update. Fast updates plus
Quantum-Safe Code Auditing: LLM-Assisted Static Analysis and Quantum-Aware Risk Scoring for Post-Quantum Cryptography Migration
arXiv:2604.00560v1 Announce Type: cross Abstract: The impending arrival of cryptographically relevant quantum computers (CRQCs) threatens the security foundations of modern software: Shor's algorithm breaks RSA, ECDSA, ECDH, and Diffie-Hellman, while Grover's algorithm reduces the effective security of symmetric and hash-based schemes. Despite NIST standardising post-quantum cryptography (PQC) in 2024 (FIPS 203 ML-KEM, FIPS 204 ML-DSA, FIPS 205 SLH-DSA), most codebases lack automated tooling to inventory classical cryptographic usage and prioritise migration based on quantum risk. We present Quantum-Safe Code Auditor, a quantum-aware static analysis framework that combines (i) regex-based detection of 15 classes of quantum-vulnerable primitives, (ii) LLM-assisted contextual enrichment to c
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!