Rail Vision Granted Key Patent in Europe for Advanced AI-Based Railway Collision Avoidance System

Rhea-AI Summary

Rail Vision (Nasdaq: RVSN) announced that the European Patent Office granted a patent on December 15, 2025 for its AI-based railway collision avoidance method and system.

The patent covers a forward-looking single-spectrum or multispectral electro-optical imaging approach, a novel system architecture and deep learning-based scene analysis using a two-stage CNN process: one CNN to determine the railway path and a secondary CNN to detect obstacles in real time. The system issues alarms for switches, obstructions, end-of-rail conditions and other hazards, supporting manned operation decision-making and enabling automated decisions for driverless trains.

This European grant builds on prior patent approvals in the United States, Japan, and India, reinforcing the company’s global IP protection for its AI, sensor and data technologies.

Positive

• European Patent Office grant on Dec 15, 2025
• Patent covers multispectral electro-optical imaging and novel architecture
• Two-stage CNN process for path detection and real-time obstacle detection
• Supports both manned decision support and automated driverless decisions
• Builds on prior approvals in the US, Japan, and India

Negative

• None.

News Market Reaction – RVSN

-6.04%

6 alerts

-6.04% News Effect

+2.2% Peak Tracked

-9.9% Trough Tracked

-$1M Valuation Impact

$21M Market Cap

0.6x Rel. Volume

On the day this news was published, RVSN declined 6.04%, reflecting a notable negative market reaction. Argus tracked a peak move of +2.2% during that session. Argus tracked a trough of -9.9% from its starting point during tracking. Our momentum scanner triggered 6 alerts that day, indicating moderate trading interest and price volatility. This price movement removed approximately $1M from the company's valuation, bringing the market cap to $21M at that time.

Data tracked by StockTitan Argus on the day of publication.

Market Reality Check

Price: $8.39 Vol: Volume 662,648 is about 0...

normal vol

$8.39 Last Close

Volume Volume 662,648 is about 0.87x the 20-day average of 763,765, not indicating unusual activity before this patent news. normal

Technical Shares at 0.3542 were trading below the 200-day moving average of 0.4 and sat 86.98% under the 52-week high, though still 29.55% above the 52-week low.

Peers on Argus

Sector peers showed mixed, modest moves pre-news: SWVL (-1.3%), RAIL (-0.31%), G...

Sector peers showed mixed, modest moves pre-news: SWVL (-1.3%), RAIL (-0.31%), GBX (-0.84%), CVV (-0.3%), while FSTR gained 1.06%. No broad, unified sector momentum was evident around this announcement.

Historical Context

5 past events · Latest: Dec 01 (Positive)

Pattern 5 events

Date	Event	Sentiment	Move	Catalyst
Dec 01	Acquisition agreement	Positive	-1.9%	Definitive agreement to acquire 51% of Quantum Transportation with loan funding.
Oct 15	Conference appearance	Neutral	-6.5%	Announcement of LD Micro Main Event XIX presentation and investor meetings.
Oct 09	AI acquisition term sheet	Positive	-3.5%	Non-binding term sheet for 51% Quantum Transportation stake and convertible loan.
Sep 30	AI acquisition term sheet	Positive	+9.3%	Initial term sheet to acquire 51% of Quantum Transportation with $700k loan.
Sep 03	Nasdaq compliance extension	Positive	+12.6%	180-day extension to regain $1.00 minimum bid price listing compliance.

Pattern Detected

Recent news often met with mixed or negative price reactions, even for seemingly strategic or positive items, with a few strong upside exceptions.

Recent Company History

Over the last six months, Rail Vision has balanced listing compliance, M&A, and visibility efforts. On Sep 3, 2025, it secured a 180-day Nasdaq bid-price extension, which saw a 12.64% gain. Multiple AI-focused Quantum Transportation acquisition announcements between Sep 30 and Dec 1, 2025 drew varied reactions, from -3.55% to 9.34%. A conference appearance on Oct 21, 2025 coincided with a -6.5% move, highlighting that even neutral news sometimes preceded selling pressure.

Market Pulse Summary

The stock moved -6.0% in the session following this news. A negative reaction despite positive IP ne...

Analysis

The stock moved -6.0% in the session following this news. A negative reaction despite positive IP news would fit a pattern where strategic updates previously met selling pressure. The European patent extends protection for Rail Vision’s AI-based collision avoidance system and supports its automation ambitions, but investors have at times focused more on listing compliance and deal structures. In such cases, concerns about execution, timelines, or broader market risk appetite could overshadow the long-term potential of new patents.

Key Terms

electro-optical imaging, deep learning, convolutional neural network

3 terms

electro-optical imaging technical

"utilizing forward-looking single-spectrum or multispectral electro-optical imaging"

Electro-optical imaging is a technology that captures visual information by converting light into electrical signals using sensors and lenses, similar to how a digital camera records a scene. Investors care because it underpins products like surveillance cameras, satellites, medical scanners and industrial sensors; improvements can drive revenue growth, open new markets, reduce costs, or create competitive advantage in sectors where better image quality or faster sensing matters.

deep learning technical

"advanced scene analysis powered by deep learning"

Deep learning is a type of artificial intelligence that uses multiple layers of computer models to recognize patterns and make decisions from large amounts of data, similar to how someone improves at a task by practicing many examples. Investors care because companies that harness deep learning can automate work, improve products, cut costs or create new revenue streams — but adoption also involves investment, data and regulatory risks that can influence profits and valuation.

convolutional neural network technical

"The technology employs a unique Convolutional Neural Network (CNN) process"

A convolutional neural network is a type of artificial intelligence model that finds and classifies patterns in images or other structured data by passing information through a series of automated filters that pick out edges, shapes and important features. For investors, CNNs matter because they power products like image-based diagnostics, visual quality control and autonomous systems, enabling faster, cheaper or more accurate services that can increase revenue, cut costs and create competitive advantage.

AI-generated analysis. Not financial advice.

The patent reinforces Rail Vision’s global IP protection building on previous approvals in regions including the United States, Japan, and India

Ra’anana, Israel, Dec. 15, 2025 (GLOBE NEWSWIRE) -- Rail Vision Ltd. (Nasdaq: RVSN) (“Rail Vision” or the “Company”), an early commercialization stage technology company seeking to revolutionize railway safety and the data-related market, today announced that the European Patent Office has granted a patent for its innovative railway collision avoidance method and system.

This newly granted European patent covers an innovative approach utilizing forward-looking single-spectrum or multispectral electro-optical imaging, combined with a novel system architecture and advanced scene analysis powered by deep learning. The technology employs a unique Convolutional Neural Network (CNN) process to first accurately determine the railway path ahead of the locomotive or train. A secondary object detection CNN then analyses the vicinity of the identified path to detect potential obstacles in real time.

The system generates critical alarms for a wide range of hazards, including railway switch occurrences and states, obstructions, impending end-of-rail effects and various types of obstacles. The patented technology delivers advanced scene understanding, providing essential decision support for locomotive drivers in manned operations and enabling fully automated decision-making for driverless trains.

The patent reinforces Rail Vision’s global IP protection strategy, building on previous approvals in regions including the United States, Japan, and India. It further solidifies the company’s position as an innovator in transforming railway operations with AI, big data, and advanced sensor technologies.

About Rail Vision Ltd.

Rail Vision is a development stage technology company that is seeking to revolutionize railway safety and the data-related market. The company has developed cutting edge, artificial intelligence based, industry-leading technology specifically designed for railways. The company has developed its railway detection and systems to save lives, increase efficiency, and dramatically reduce expenses for the railway operators. Rail Vision believes that its technology will significantly increase railway safety around the world, while creating significant benefits and adding value to everyone who relies on the train ecosystem: from passengers using trains for transportation to companies that use railways to deliver goods and services. In addition, the company believes that its technology has the potential to advance the revolutionary concept of autonomous trains into a practical reality. For more information, please visit https://www.railvision.io/

Forward-Looking Statements

This press release contains “forward-looking statements” within the meaning of the Private Securities Litigation Reform Act and other securities laws. Words such as “expects,” “anticipates,” “intends,” “plans,” “believes,” “seeks,” “estimates” and similar expressions or variations of such words are intended to identify forward-looking statements. Such expectations, beliefs and projections are expressed in good faith. For example, Rail Vision is using forward-looking statements when it discusses its position as an innovator in transforming railway operations with AI, big data, and advanced sensor technologies. The Company cannot assure that any patent will issue as a result of a pending patent application or, if issued, whether it will issue in a form that will be advantageous to the Company. However, there can be no assurance that management’s expectations, beliefs and projections will be achieved, and actual results may differ materially from what is expressed in or indicated by the forward-looking statements. Forward-looking statements are subject to risks and uncertainties that could cause actual performance or results to differ materially from those expressed in the forward-looking statements. For a more detailed description of the risks and uncertainties affecting the Company, reference is made to the Company’s reports filed from time to time with the Securities and Exchange Commission (“SEC”), including, but not limited to, the risks detailed in the Company’s annual report on Form 20-F filed with the SEC on March 31, 2025. Forward-looking statements speak only as of the date the statements are made. The Company assumes no obligation to update forward-looking statements to reflect actual results, subsequent events or circumstances, changes in assumptions or changes in other factors affecting forward-looking information except to the extent required by applicable securities laws. If the Company does update one or more forward-looking statements, no inference should be drawn that the Company will make additional updates with respect thereto or with respect to other forward-looking statements. References and links to websites have been provided as a convenience, and the information contained on such websites is not incorporated by reference into this press release. Rail Vision is not responsible for the contents of third-party websites.

Contacts
David BenDavid
Chief Executive Officer
Rail Vision Ltd.
15 Ha'Tidhar St
Ra'anana, 4366517 Israel
Telephone: +972- 9-957-7706

Investor Relations:
Michal Efraty
investors@railvision.io

FAQ

What did Rail Vision (RVSN) announce on December 15, 2025?

Rail Vision announced a European Patent Office grant for its AI-based railway collision avoidance system.

What technology does the RVSN European patent cover?

The patent covers single-spectrum or multispectral electro-optical imaging, a novel system architecture and deep-learning scene analysis using two CNNs.

How does the patented system detect hazards according to Rail Vision (RVSN)?

A primary CNN determines the railway path ahead and a secondary CNN analyzes the path vicinity to detect obstacles and generate critical alarms in real time.

Does the RVSN patent support driverless train operation?

Yes, the patent is described as enabling fully automated decision-making for driverless trains and decision support for manned operations.

Has Rail Vision (RVSN) received similar patent approvals elsewhere?

Yes, the company previously received patent approvals in the United States, Japan, and India.

What hazards does the Rail Vision (RVSN) system claim to detect?

The system is described as generating alarms for railway switch occurrences and states, obstructions, end-of-rail effects and various obstacle types.