Connect with us

Gadgets

Koala-sensing drone helps keep tabs on drop bear numbers – TechCrunch

Published

on

It’s obviously important to Australians to make sure their koala population is closely tracked — but how can you do so when the suckers live in forests and climb trees all the time? With drones and AI, of course.

A new project from Queensland University of Technology combines some well-known techniques in a new way to help keep an eye on wild populations of the famous and soft marsupials. They used a drone equipped with a heat-sensing camera, then ran the footage through a deep learning model trained to look for koala-like heat signatures.

It’s similar in some ways to an earlier project from QUT in which dugongs — endangered sea cows — were counted along the shore via aerial imagery and machine learning. But this is considerably harder.

A koala

“A seal on a beach is a very different thing to a koala in a tree,” said study co-author Grant Hamilton in a news release, perhaps choosing not to use dugongs as an example because comparatively few know what one is.

“The complexity is part of the science here, which is really exciting,” he continued. “This is not just somebody counting animals with a drone, we’ve managed to do it in a very complex environment.”

The team sent their drone out in the early morning, when they expected to see the greatest contrast between the temperature of the air (cool) and tree-bound koalas (warm and furry). It traveled as if it was a lawnmower trimming the tops of the trees, collecting data from a large area.

Infrared image, left, and output of the neural network highlighting areas of interest

This footage was then put through a deep learning system trained to recognize the size and intensity of the heat put out by a koala, while ignoring other objects and animals like cars and kangaroos.

For these initial tests, the accuracy of the system was checked by comparing the inferred koala locations with ground truth measurements provided by GPS units on some animals and radio tags on others. Turns out the system found about 86 percent of the koalas in a given area, considerably better than an “expert koala spotter,” who rates about a 70. Not only that, but it’s a whole lot quicker.

“We cover in a couple of hours what it would take a human all day to do,” Hamilton said. But it won’t replace human spotters or ground teams. “There are places that people can’t go and there are places that drones can’t go. There are advantages and downsides to each one of these techniques, and we need to figure out the best way to put them all together. Koalas are facing extinction in large areas, and so are many other species, and there is no silver bullet.”

Having tested the system in one area of Queensland, the team is now going to head out and try it in other areas of the coast. Other classifiers are planned to be added as well, so other endangered or invasive species can be identified with similar ease.

Their paper was published today in the journal Nature Scientific Reports.

Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Gadgets

Apple Watch Ultra becomes a diving computer with launch of Oceanic+

Published

on

In September, Apple announced a new wearable called the Apple Watch Ultra, and one of the company’s key pitches for the device was its use as a diving computer. Now Oceanic+, the app that makes that feature possible, launched exclusively for the Ultra, Apple announced today.

The Watch Ultra has depth gauge and water temperature sensors that drive some of the features in the app. To access a few of those features—such as decompression tracking—you’ll have to subscribe to the app’s premium version for $4.99 per day, $9.99 per month, or $79.99 per year. There’s also a family plan at $129.99 annually. If you don’t subscribe, you can still use some key features like dive logs, depth tracking, and so on.

The app—which was developed in partnership with Apple by a company called Huish Outdoors, lets you track dive conditions like tides, water temperature, and more. Here’s a quick summary from Apple’s blog post announcement:

In the dive planner, users can set their surface time, their depth, and their gas, and Oceanic+ will calculate their No Deco (no-decompression) time—a metric used to determine a time limit for a diver at a certain depth. The planner also integrates dive conditions, including tides, water temperature, and even up-to-date information from the community, such as visibility and currents. Post-dive, users will see data—including GPS entry and exit locations—automatically pop up on Apple Watch Ultra, along with a summary of their dive profile. The summary on the Oceanic+ iPhone app provides additional information, including a map of entry and exit locations, as well as graphs of depth, temperature ascent rate, and no-decompression limit.

A lot of the features focus on either planning dives in advance or viewing dive reports after you’re done, but for those that you use underwater, the app utilizes haptics to send you alerts. The Watch Ultra’s very bright screen can help with legibility underwater, too.

The app doesn’t work with other Apple Watch models. To use it, you’ll need an Apple Watch running watchOS 9.1, and that Watch must be paired with an iPhone 8 or later running iOS 16.1.

Listing image by Samuel Axon

Continue Reading

Gadgets

Regulatory filings suggest Nvidia’s scrapped RTX 4080 will return as the “4070 Ti”

Published

on

Nvidia

Last month, Nvidia took the unusual step of “unlaunching” a previously announced product. The 12GB version of the GeForce RTX 4080 graphics card was, by the company’s admission, “not named right” and was delayed and rebranded to avoid confusion with the 16GB version of the RTX 4080 that launched. Besides having less RAM, the 12GB version of the RTX 4080 also offered less memory bandwidth and fewer GPU cores than the 16GB version.

Nvidia didn’t announce exactly what branding it would use for the revived RTX 4080, but regulatory filings submitted by Gigabyte (as reported by VideoCardz) suggest that the company has settled on calling it the “4070 Ti.”

This isn’t guaranteed to be the actual name—regulatory filings like this can be placeholders rather than actual products—but this branding would be more consistent with how Nvidia has named past GPU generations. The xx80 cards usually use the same physical GPU die as the flagship xx90 cards but run at lower clock speeds and with parts of the die switched off; this allows Nvidia to use GPU dies with defects rather than tossing them out. The xx70 cards generally use a smaller, less-performant GPU die based on the same architecture.

Nvidia made the rebranding decision late enough in the process that it reportedly caused Nvidia and its partners to throw out finished packaging and other elements with “4080” branding. Redesigning and then re-manufacturing those things takes time, as does re-flashing the BIOSes on already-manufactured graphics cards so that they identify themselves as 4070 Tis rather than 4080s.

Nvidia still hasn’t said whether the price of the cards would also come down along with the model number; the 12GB version of the RTX 4080 was originally slated to launch for $899, while the RTX 3070 Ti was originally launched at $599. But existing RTX 4090 and 4080 cards are already difficult to get anywhere near their already-high $1,600 and $1,200 starting prices. It may be that an RTX 4070 Ti with decent 4K gaming performance, DLSS 3 support, and the other RTX 4000-series architectural bells and whistles would still sell out even with a big generation-over-generation price hike.

Continue Reading

Gadgets

Google says Google should do a better job of patching Android phones

Published

on

Google’s “Project Zero” team of security analysts wants to rid the world of zero-day security vulnerabilities, and that means it spends time calling out slacking companies on its blog. The group’s latest post is a bit of friendly fire aimed at the Android and Pixel teams, which Project Zero says aren’t dealing with bugs in the ARM GPU driver quickly enough.

In June, Project Zero researcher Maddie Stone detailed an in-the-wild exploit for the Pixel 6, where bugs in the ARM GPU driver could let a non-privileged user get write access to read-only memory. Another Project Zero researcher, Jann Horn, spent the next three weeks finding related vulnerabilities in the driver. The post says these bugs could allow “an attacker with native code execution in an app context [to] gain full access to the system, bypassing Android’s permissions model and allowing broad access to user data.”

Project Zero says it reported these issues to ARM “between June and July 2022” and that ARM fixed the issues “promptly” in July and August, issuing a security bulletin (CVE-2022-36449) and publishing fixed source code. But these actively exploited vulnerabilities haven’t been patched for users. The groups dropping the ball are apparently Google and various Android OEMs, as Project Zero says that months after ARM fixed the vulnerabilities, “all of our test devices which used Mali are still vulnerable to these issues. CVE-2022-36449 is not mentioned in any downstream security bulletins.”

The affected ARM GPUs include a long list of the past three generations of ARM GPU architectures (Midgard, Bifrost, and Valhall), ranging from currently shipping devices to phones from 2016. ARM’s GPUs aren’t used by Qualcomm chips, but Google’s Tensor SoC uses ARM GPUs in the Pixel 6, 6a, and 7, and Samsung’s Exynos SoC uses ARM GPUs for its midrange phones and older international flagships like the Galaxy S21 (just not the Galaxy S22). Mediatek’s SoCs are all ARM GPU users, too, so we’re talking about millions of vulnerable Android phones from just about every Android OEM.

In response to the Project Zero blog post, Google told Engadget, “The fix provided by Arm is currently undergoing testing for Android and Pixel devices and will be delivered in the coming weeks. Android OEM partners will be required to take the patch to comply with future SPL requirements.”

The Project Zero analysts end their blog post with some advice for their colleagues, saying, “Just as users are recommended to patch as quickly as they can once a release containing security updates is available, so the same applies to vendors and companies. Minimizing the ‘patch gap’ as a vendor in these scenarios is arguably more important, as end users (or other vendors downstream) are blocking on this action before they can receive the security benefits of the patch. Companies need to remain vigilant, follow upstream sources closely, and do their best to provide complete patches to users as soon as possible.”

Continue Reading

Trending