Nexar Crash Prediction Challenge Winners Revealed: Pioneering AI for Safer Roads
The Nexar Crash Prediction Challenge attracted remarkable global participation, with 282 team participants and 1,625 submissions.
Automotive
CityStream Live’s Real-Time Mapping Platform has Kickstarted a Revolution - Here’s Why
Software is eating the roads. This might seem like a grand statement, but in the 7 years since I co-founded Nexar with Bruno Fernandez-Ruiz, it has also become glaringly apparent. In practice, this means that vehicles are becoming increasingly software-centric - prioritizing the consumer demand and experience. The implications are
How AI is Transforming Navigation Maps - and the World
Nexar’s Algorithm Data Analyst, Raphael Mamane, explains how the company is paving the way for the future of digital maps - and revolutionizing the world as we know it In the era of automation and efficiency we are approaching, traditional maps are no longer sufficient. As maps move from
Parking and curb-space: can you map it in real-time?
What it takes to create a crowd-sourced identification of free, on-street, parking During February 2021 we used images collected from dash cams and AI to map on-street parking spots in Milan. We wanted to understand the city’s curb-side and prove the value of real-time, free-parking-spot detections for drivers and
Announcing AI-Powered Image Retrieval method for Better Localization in Cities
A comparison between the driver’s accurate location (green dots) and the raw GPS data (red) Today we are very excited to announce that Nexar has developed a new, AI-powered visual localization method that greatly improves GPS location accuracy in challenging urban environments. We’re presenting this new method today
The Case for Continuous Deep Learning at The Edge
Edge devices and very large real-world driving datasets hold the promise of autonomous driving Over the past few years, we’ve seen significant advances in learning-based approaches to the development of automotive safety applications. These advances have been applied predominantly to the perception stage of autonomous driving systems. The decisioning
Will We Actually Stop Buying Cars?
We’re all hearing and now talking about the inevitability of us ditching car ownership in the future. It’s coming from all sides. > “Uber will take over the world (as long as they can get out of their own way)”. “No one will own a car anymore”. “Millennials
The Anatomy of Crashes in NYC
We’re only human, right!? It’s a fact that 95% of car collisions are caused by human error. The autonomous vehicle has been heralded as the future road-messiah that will take the wheel and save us from self-inflicted pain and loss. However, it’s important to remember that it
Nexar’s Deep Learning Challenge: the winners reveal their secrets
We challenged researchers with teaching deep networks to identify traffic lights, and now they share what they learned in the process. Read on for their insights and a look at their open-source models. Deep learning plays a key role in the race to autonomous vehicles and we wanted to open
Data Collection Obsession: The Key to Disrupting the Automotive Industry?
As we sail through the vast technological oceans of 2023, decision-makers across the globe are contemplating how the formidable blend of generative AI and big data is instigating a revolution in the automotive sector. Today, we’re retracing the incredible progress made in the domains of big data, deep learning,
Real-Time Mapping: A glossary of top 100+ terms and acronyms (Pt. 2)
This glossary offers over 100 definitions for common terms in the context of real-time mapping. As a guiding principle, we opted to include generally accepted definitions as well as to explain (whenever appropriate) how each entry applies to the key concepts in real-time mapping. Part one can be found here
An Autonomous Map for the Autonomous Era
Today we published a report comparing the ground truth speed limit signs in Phoenix, AZ, with OSM and City of Phoenix data. The bottom line is that maps become stale at a rate of 2.5-6% per year and that we need to change how we think about map creation,
Imagining vision-based connected car camera applications
By 2024 most new car models will include several built-in cameras. Cameras are there for the cars to “see” — the road, cyclists, pedestrians, road signs and more. Most industry pundits focus on the use of car-sight as cars evolve to self-driving. Yet, even before, during and after self-driving becomes a
Is DSRC dead? Vehicle to vehicle mobility network interoperability with LISP
Toyota’s recent announcement to halt the deployment of 802.11p (DSRC or ITS-G5) vehicle-to-vehicle technology in new cars may come as a surprise to some.
Cars, safety, and cameras
A bridge to our autonomous driving future We’ve talked in previous posts about the challenges autonomous vehicles (AVs) could bring or worsen — traffic [https://blog.getnexar.com/traffic-wont-go-away-with-autonomous-cars-d136f22288a8] , time to market [https://blog.getnexar.com/buckle-up-transportation-will-completely-change-in-40-years-c75c5e46845c] , and ridesharing [https://blog.getnexar.com/ridesharing-and-carsharing-is-a-sideshow-54a253d58100] . However, they’re without a doubt
Buckle up! Transportation will Completely Change…In 40 Years
First post in a five-part series about how transportation will evolve as an ecosystem It will take 40 years for autonomous vehicles to replace human drivers across the world. Despite the hype and Tesla’s best efforts, it will not take 20 or 10 years, and definitely not 5. A
“Data is the new oil”
Why the race for data ownership is the new driving force of the automotive industry. Yesterday Intel & Mobileye announced that Mobileye will be acquired by Intel for over $15B, an announcement that made waves, given its sheer size and importance, not just for the Israeli tech ecosystem, where Intel
Cars, roads, and driving have evolved - but yesteryear’s maps are dead
Maps are becoming outdated, as the traditional method of manual curation and editing is just not feasible - especially for ADAS and AVs. It's time for a change in the paradigm and for live maps to help the driving task. The maps of yesteryear are dead. The purpose
Real-Time Mapping: A glossary of top 100+ terms and acronyms (Pt. 1)
This glossary offers over 100 definitions for common terms in the context of real-time mapping. As a guiding principle, we opted to include generally accepted definitions as well as to explain (whenever appropriate) how each entry applies to the key concepts in real-time mapping. A Advanced Driver Assistance Systems (ADAS)
Automotive Edge Model: Lessons learned from legacy V2V and V2C
AECC recently published an architecture whitepaper [https://aecc.org/resources/publications/] for mobility & connected cars - "Distributed Computing in an AECC System". As Nexar is a part of the AECC, we’re excited to take in part in this architecture and share the highlights of this whitepaper.
How car camera applications can help us understand the cost differences for endpoint, edge or cloud AI/compute
In the next 3–5 years, all new cars will contain cameras. Several cameras per car, actually. Will car cameras remain confined to driving assist functions, or will they evolve into a new way of seeing and sensing the roads and the world around them? The question of what can
Smarter Cities for the Cars of the Future
Autonomous Vehicles Require a New City Model Over the course of the last several weeks we’ve talked about the many effects and even needs of autonomous vehicles as we work towards a future filled with them. We’ve debated whether people will buy fewer or exponentially more cars with
Traffic Won’t Go Away With Autonomous Cars
Traffic in Beijing. Fu Ding / For China DailyWe all feel it — traffic is getting worse and worse. Congestion periods have slowly expanded beyond commute times and become an all-day phenomenon. Our commute gets longer and longer with every passing year. In previous posts, we discussed how long it’ll take
It’s All Corner Cases: Teaching Computers to Drive Safely
Also introducing our latest data challenge for autonomous developers [https://www.getnexar.com/challenge-2/]` It could be argued there is only one proven Big Data application — web search. Nothing so far has met the sheer size and complexity of indexing the web at the precision, recall, and freshness Google delivers.
January Update: Our Top 5 Videos from Last Month
In January we saw jaywalkers and jay-bikers, falling telephone poles and strange skateboarding. Take a look at some of the craziest moments shared by our users. Each month, we give you the videos captured by Nexar’s users that created the biggest reactions in the community. Some are just for