Visage Technologies

Imagine an ADAS perception system designed to operate on rural roads, where tractors are part of the expected operational environment. If the dataset specification does not include a tractor class, the problem exists before a single model is trained. Tabl

Computer vision is already well established across pharmaceutical R&D and manufacturing. It supports applications ranging from automated visual inspection and quality control to digital pathology, laboratory automation and microscopy image analysis. As AI

Few industries operate under the same combination of scientific complexity, regulatory oversight, and quality requirements as the pharmaceutical industry. Every stage of research, development, and manufacturing generates information that must be interpret

In December 2024, ISO published ISO/PAS 8800, the first international specification focused on the safety of AI in road vehicles. It introduces guidance for challenges that are specific to AI, including data quality, model uncertainty, and continuous vali

Autonomous industrial vehicles have become highly effective at detecting obstacles and navigating complex environments. However, in mining, quarrying, construction, and agriculture, an enduring challenge continues to hinder perception performance: Dust. U

In the off-highway sector, AI models are improving fast. Deployment challenges are not. Artificial intelligence started transforming the off-highway industry, driving efficiency, safety, and automation in equipment such as autonomous agricultural and mini

Freight swarms are not robotic insects carrying cargo. They are coordinated systems where fleets of autonomous vehicles move as one, optimizing how freight flows in real time. While this concept is still in its early stages, it points toward a future in w

Summary This proof of concept (PoC) explores real-time detection, tracking, and motion prediction of small UAVs using thermal imaging on embedded hardware. This approach integrates long-wave infrared sensing, temporal tracking, and predictive modeling to

A flawed data pipeline can lead to mistakes, crashes, or failures. Real-world incidents highlight that system reliability depends on detection algorithms, but also on how data is processed and interpreted throughout the pipeline. In the 2018 Uber automate

About the team For the last 6 months, a small team consisting of 2 of my team mates and me has been deeply entrenched into researching LLM's, agentic frameworks, tools, MCP, and other related terms one has to master to navigate the AI space. We feel that