anh_n

Workout Live is a simple iOS app to view live workout data (heart rate, calories) from Apple Watch.

No ads, no profile tracking, no registration and completely free.

I just wanted to watch my heart rate on the phone screen while doing the workout. There are some apps which can do it but with subscription and too many features I don’t need. The best case would be that the built-in Apple Fitness app has this feature, but it hasn’t. So, I decided to spend my weekend writing this app. I use it just during workout. For analysis or viewing histories, I use the built-in Health or Fitness app.

I am not sure if most of those people who care about privacy is also technically able to self host a server. But this maybe an option too.

I am working on something like that. Use computer vision to detect anomaly. If you are interested you can subscribe a newsletter to get notified when the feature is out at ai-cam.app

A server has more compute power but only needed if the problem to solve requires such power. In my last company I developed a visual search system (similar to Google Image Search) and for that use cases a powerful server is required. But for the problems this app try to solve like human detection or facial recognition, a mobile device is very capable of. In the last 2-3 years the new phones also has integrated AI chip, which make the task easier.

I am personally using an expensive Nest IQ cam (cost around 300 USD) and some cheap IP camera in parallel with this AiCam app. For me the physical security camera are good to install outside my house or where I do not care if the video footage may be leaked or hacked.

But I have some use cases which I did not find any security camera suited for it, it also the reason why I developed this app:

- I want to monitor my sleeping room, but I trust no security camera brands.

- I want to integrate the camera into my home automation system and use event like person, animal detected to trigger some workflows.

- I want to detect more complex events like unfamiliar faces, fire, baby crying and not just simple motion or sound to avoid false alarms. This is the main point why a phone is more suitable, because most smartphones have required compute power to do all the AI work offline.

- Also a mobile phone have some additional advantages like you mentioned (integrated battery as UPS), cellular network as a backup to send alert when power or internet is down.

All in all it depends on what features are you expected from a security camera.

There are some similar apps which can turn your phone into a security camera (e.g. Alfred, Presence). AiCam is different because it runs all machine learning algorithm offline on-device. It does not store or send video to a remote server (actually we do not have a server). Only if you (optionally) turn on iCloud sync you can save videos directly to your private iCloud account for remote accessing. Some of its features are:

- On-device ML to detect human, animal, vehicle and recognize unfamiliar face.

- Integration with Shortcuts app for home automation and sending webhook request on event detected.

- With privacy-first in mind, it does not collect any data, it has no ads, no tracking tool integrated. Video is processed offline on-device.

The premium version with all features unlocked can be bought for a one-time fee. There is also a free version (no ads) with limited features but can use forever (no time limit).

My teammate did post asking for beta users some time ago (https://news.ycombinator.com/item?id=26123763). We received a lot of value feedbacks. Now the iOS app is passed beta phase and is available on App Store. Android is still in beta though. We did also redesign our website completely to provide more helpful information. Feedback is always welcome. Specially I love to know which features you would like this app to have?

Cool idea. I developed an iOS app with the same idea (https://www.ai-cam.app) but I think being able to run on browser can target more users.

If you have an old iPhone, you might want to checkout AiCam http://ai-cam.app. It has some smart features like person detection. It can work completely offline. Disclaimer: I am the developer of the app.

Thanks for your suggestion. But are these functionalities not better implemented on a desktop computer? A mobile phone is limited in compute capability but very portable, so it easy to use it for occasional situation like when traveling, or when you only need a security camera for a short time and do not want to invest much.

Those from Eufy are physical cameras. Their mobile app is used to control their camera. But this one "ai-cam" is a mobile app which use phone camera and do not require another physical camera. Also the smart alerts of "ai-cam" are much more advanced.

An Android version is also planned.

This app focus on running on-device AI algorithms so it needs latest OS software in able to do it.

You need to plug it to a power source because the AI algorithms run on-device require energy.

You can optionally turn on iCloud synchronization, then videos will be uploaded to your iCloud account.

I can not tell much about the model architecture. We have some proprietary technology to reduce the amount of images needed for training and to increase accuracy.

The number of images depends on several factors like the total number of objects, the variation of images, visually difference between objects, etc.

We have developed some proprietary technology to reduce the amount of images needed. In general each object should have 10-100 images to avoid overfit.

Yes, there will be an API to use the object recognizer with other apps or website. We have pre-made both the iOS and Android app because many users can not or do not have time to create the app.

And yes it will also work with any symbols or diagrams rendered on screen. Almost everything we human can visually recognize will work.

The name Lookuq came from "look up" and should have the same meaning. But the domain lookup.com is not available. So we just switched the last character from "p" to "q" to have the domain. We pronounce Lookuq as "look up".

Hi all, I am co-founder of Lookuq and want to explain a bit more about our idea.

There is a lot of apps to recognize some things. Popular example are PlantNet, PlantSnap for recognizing plants. They all have similar functionality, you take a picture of the object and then the app show you a list of objects it thinks what is it. Click on it, you can see more information about the object.

There are many things which visual identification is helpful, e.g. dog breed, animal, plant species, vintage watches, artworks, ...

Everyone is expert in something and may have a lot of images of the objects and information about it. They should be able to share this knowledge to other people.

With our Lookuq platform, it is super easy to create an object recognizer app without coding. All you need is photos of the objects and some information about the objects in tabular form (CSV, Excel format). Then you can upload it to our website, let the system automatically create and train the model to recognize the objects. After that just use our pre-made app (available on both iOS and Android) to recognize the objects and show related information to the objects.

I would love to know what you think about it?