Use Computer Vision to Analyze Your Imagery

At Xyonix, we use state of the art computer vision to automatically see and distill valuable insights across your image, video and LiDAR collections.

Modern applications generate incredible amounts of imagery; if mined effectively, these images and videos can provide valuable insights. In order to effectively mine imagery, we must teach machines to see these vast collections and understand the content. State of the art computer vision (CV) technologies allow us to leverage hard fought machine knowledge gained from public imagery available on the Internet. CV capabilities can help in multiple areas like video segmentation, imagery quantification, or body pose analysis.

Featured

“I don’t think a five out of five really encapsulates the work that they do. The work is top-notch. It’s what we ask for and more. They go the extra mile in terms of letting us know that whatever we need, they’re there for us to lend their expertise, to be in a meeting if they need to, to explain the project in more detail. So it’s really going above and beyond.”

Dominique Grinnell, Sr. Product Team Manager at Delta Dental of Washington [more]

Our Capabilities are showcased by some of our Recent CV Projects:

AI Driven Video Summarizer

For an extremely rapidly growing startup, we built an AI system that transforms lengthy, often instructional videos into concise, optimized segments. The system cleanses transcripts, then leverages LLM models we fine tuned using training data meticulously annotated by a combination of other LLMs and our human team at Xyonix. It's adept at extracting key topics, generating summaries, easing navigation, and producing short, impactful videos in various formats. Already in public use and benefiting millions daily, this system is a game-changer for educational and instructional content, making complex information more accessible and engaging.

Video Content Creator

In collaboration with a rapidly growing startup, we've crafted an AI-driven solution for helping users rapidly create high-quality video content by automatically analyzing user generated movie scripts and identifying optimal video assets for inclusion in short videos. Our role extended beyond data science; we engineered and now host a fully scaled system. This platform excels in generating scene text and keywords, leveraging semantic search within a bespoke imagery index, and creating video metadata from video frames. Designed to facilitate the production of engaging videos and scripts for social media and advertising, this service is robust, fully managed, and caters to millions of users daily.

AI Med Spa Assistant

Xyonix teamed up with an early-stage startup to launch an AI iPhone app based assistant to help Med Spa nurse practitioners. The AI technology adeptly categorized facial features, aiding in the assessment of treatments and spotting issues like temporal visual changes, ineffective product batches or injector performance. Integrated with iOS for precise patient driven photo alignment, the system enabled consistent treatment tracking. We played a pivotal role in technology development and strategic product planning; our involvement was key in fusing medical accuracy with technological innovation in product development. [Read more]

AI Backed Surgery

For a fortune 500 company, our Xyonix built models are in production today constantly analyzing thousands of recent in body surgery videos and reviews across many hundreds or thousands of surgery rooms around the world. Our models watch never ending streams of surgery videos, and read countless reviews. Our models power dashboards that help surgeons improve. [Read more]

Early Developmental Risk Screener

We helped our client build out automated tools for early motor development risk and autism spectrum screening. Automatically and accurately extracting an infant’s pose and understanding these movements over time can be essential in preventing a lifetime of problems.

AI Endoscope

We trained an AI system to automatically detect cancerous lesions from a customer’s novel disposable endoscope. Our system can help physicians detect lesions including papillary carcinomas in procedures like a cytoscopy.

Penalty Kick Activity Analyzer

Can we better an individual goalie’s chances of stopping a penalty kick with advanced AI? Many of us at Xyonix are huge soccer fans. With the recent excitement of the 2019 FIFA Women’s World Cup, and the success of the U.S. Women’s National Team, we got inspired to try and apply advanced AI techniques to soccer. The results helped us work out the kinks in our activity analysis platform.

Running Gait Analyzer

Can amateur runners improve their performance using artificial intelligence and nothing more than a smart phone? As an AI practitioner and a dedicated runner, one of our resident data scientists decided to find out. The results led us to building out the activity analysis platform.

Want to learn more? Check out Our Recent CV Related Articles

Farming is Dying – Can AI and AgTech Save It?

The global food supply is on the brink of crisis. Facing challenges like an aging workforce, labor shortages, declining crop yields, and climate change amongst others, farming is in dire need of a lifeline. AI and AgTech are emerging as the saviors of agriculture, transforming everything from crop breeding to farm-to-table traceability. These revolutionary technologies promise to enhance sustainability, improve yields, and reduce environmental impact. With the urgency for innovation greater than ever, AI is the essential lifeline the agricultural industry needs to secure a resilient and efficient future.

Read More →

Screen Shot 2019-12-18 at 11.41.09 AM.png

Using AI Driven Video Metrics to Improve Soccer Performance

Professional athletes have long had the advantage of analysis from expensive body worn sensors. AI models, when applied to readily available video, however, offer much promise to more cost conscious amateur athletes. We ask the question, can we better an individual goalie’s chances of stopping a penalty kick with advanced AI?

Read More →

Screen Shot 2019-04-29 at 11.29.07 AM.png

Using AI to Improve Sports Performance & Achieve Better Running Efficiency

Can amateur athletes improve their performance using artificial intelligence and nothing more than a smart phone? As an AI practitioner and a dedicated runner, I decided to find out leveraging body pose estimation, an advanced AI technology that automatically generates a skeleton for people in each frame of a video.

Read More →

Drones to Robot Farm Hands, AI Transforms Agriculture

From detecting pests to predicting which crops will deliver the best returns, artificial intelligence can help humanity oppose one of its biggest challenges: feeding an additional 2 billion people by 2050 without harming the planet. AI is steadily emerging as an essential part of the agricultural industry’s technological evolution including self-driving machinery and flying robots that are able to automatically survey and treat crops.

Read More →

Screen Shot 2018-10-25 at 4.10.50 PM.png

Vannot - Video Annotation Tool for Object Segmentation

Vannot is an open source, web based, and easy to integrate video annotation tool we created to help efficiently annotate objects for use in machine learning tasks like video segmentation and imagery quantification.

Read More →

Screen Shot 2018-04-20 at 12.42.10 PM.png

Transforming Radiology and Diagnostic Imaging with AI

Throughout the diagnostic related care cycle, physicians are observing and understanding patterns. Pattern recognition is the key task for understanding the results of clinical scans. Neural networks, an automated pattern recognition capability, shows strong promise in predicting cancer and segmenting specific tumors for breast cancers, rectal cancers, and other categories of cancer that affect many Americans each year.

Read More →