{"id":1515,"date":"2022-01-31T16:54:52","date_gmt":"2022-01-31T16:54:52","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2022\/01\/31\/train-spotting-startup-gets-on-track-with-ai-and-nvidia-jetson-to-ensure-safety-cost-savings-for-railways\/"},"modified":"2022-01-31T16:54:52","modified_gmt":"2022-01-31T16:54:52","slug":"train-spotting-startup-gets-on-track-with-ai-and-nvidia-jetson-to-ensure-safety-cost-savings-for-railways","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2022\/01\/31\/train-spotting-startup-gets-on-track-with-ai-and-nvidia-jetson-to-ensure-safety-cost-savings-for-railways\/","title":{"rendered":"Train Spotting: Startup Gets on Track With AI and NVIDIA Jetson to Ensure Safety, Cost Savings for Railways"},"content":{"rendered":"
\n

Preventable train accidents like the 1985 disaster outside Tel Aviv in which a train collided with a school bus, killing 19 students and several adults, motivated Shahar Hania and Elen Katz to help save lives with technology.<\/p>\n

They founded Rail Vision, an Israeli startup that creates obstacle-detection and classification systems for the global railway industry<\/p>\n

The systems use advanced electro-optic sensors to alert train drivers and railway control centers when a train approaches potential obstacles \u2014 like humans, vehicles, animals or other objects \u2014 in real time, and in all weather and lighting conditions.<\/p>\n

Rail Vision is a member of NVIDIA Inception<\/a> \u2014 a program designed to nurture cutting-edge startups \u2014 and an NVIDIA Metropolis<\/a> partner. The company uses the NVIDIA Jetson AGX Xavier<\/a> edge AI platform, which provides GPU-accelerated computing in a compact and energy-efficient module, and the NVIDIA TensorRT<\/a> software development kit for high-performance deep learning inference.<\/p>\n

Pulling the Brakes in Real Time<\/b><\/h2>\n

A train\u2019s braking distance \u2014 or the distance a train travels between when its brakes are pulled and when it comes to a complete stop \u2014 is usually so long that by the time a driver spots a railway obstacle, it could be too late to do anything about it.<\/p>\n

For example, the braking distance for a train traveling 100 miles per hour is 800 meters, or about a half-mile, according to Hania. Rail Vision systems can detect objects on and along tracks from up to two kilometers, or 1.25 miles, away.<\/p>\n

By sending alerts, both visual and acoustic, of potential obstacles in real time, Rail Vision systems give drivers over 20 seconds to respond and make decisions on braking.<\/p>\n

The systems can also be integrated with a train\u2019s infrastructure to automatically apply brakes when an obstacle is detected, even without a driver\u2019s cue.<\/p>\n

<\/p>\n

\"\"<\/p>\n

<\/a><\/p>\n

\u201cTons of deep learning inference possibilities are made possible with NVIDIA GPU technology,\u201d Hania said. \u201cThe main advantage of using the NVIDIA Jetson platform is that there are lots of goodies inside \u2014 compressors, modules for optical flow \u2014 that all speed up the embedding process and make our systems more accurate.\u201d<\/p>\n

Boosting Maintenance, in Addition to Safety<\/b><\/h2>\n

In addition to preventing accidents, Rail Vision systems help save operational time and costs spent on railway maintenance \u2014 which can be as high as $50 billion annually<\/a>, according to Hania.<\/p>\n

If a railroad accident occurs, four to eight hours are typically spent handling the situation \u2014 which prevents other trains from using the track, said Hania.<\/p>\n

Rail Vision systems use AI to monitor the tracks and prevent such workflow slow-downs, or quickly alert operators when they do occur \u2014 giving them time to find alternate routes or plans of action.<\/p>\n

The systems are scalable and deployable for different use cases \u2014 with some focused solely on these maintenance aspects of railway operations.<\/p>\n

Watch a Rail Vision system at work<\/a>.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/2022\/01\/31\/rail-vision\/<\/p>\n","protected":false},"author":0,"featured_media":1516,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/1515"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=1515"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/1515\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/1516"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=1515"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=1515"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=1515"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}