IR-based anti-spoofing measures the quantity of light reflected from the face in the infrared image, and it does not work normally in an environment with strong visible rays.
Even though the verification server uses the HTTP method, verification failure may still occur as a result of a firewall issue if only HTTPS is allowed.
An inactivated key may have been entered or the network may be disabled.
The argument of the function sdk.initialize() receives model_path as an input. This error occurs because there are no models for execution. To correct this, specify the model path (relative/absolute) as an argument.
1. Please check the verification status.
2. Find the location of the model and license.cer file (These files don’t exist if distributed by Sentinel), and input the found path as a parameter value when initializing. Also, check whether the model path has been assigned to the function initialize.
3. Please refer to the "function Initialize" section of the Developer Guide for further details.
4. This error may occur if there is anything remaining in the cache that may be related to a previous project.
5. This error may also occur if the system period does not coincide with the license period.
1. Please check whether the license period has expired.
2. This error may occur if you have overwritten files without having first deleted the existing folder when updating bin files.
3. Please check whether the PC has been verified. This error may also occur if the PC configuration has changed.
1. Please check whether the system period is current and up to date.
2. Delete all files under the Model directory and try again.
Please delete any previous verification history.
The error may be cause by insufficient RAM. When features are enabled, please ensure that there is at least 1.3GB of memory available as this is the amount of RAM that is required for these features to function.
1. 1:N matching is not supported separately as each customer generally utilizes their own implementation method. It is however often put into use as per the following.
- Matching with the lowest value under the threshold after performing ComputerDistance.
- No return if there is no threshold value.
2. For the edge-server method, it is possible for the 1:N matching lib to be provided on the server-side. Please contact our sales team for more information.
Please verify your product by referring to and following the directions provided in the "Alchera Activator Developer Guide.pdf" file.
- For Android devices, the license verification result is dependent on the installed app.
If you update only after verification without first uninstalling, the verification will not be invalidated.
If you want to use a device-dependent license, save the activate_code in a folder independent of the app (See the guide document, page 6). This will prevent the license from being deducted when re-verified.
1. C/C++ → Preprocessor → Preprocessor definition: Change from _DEBUG → to NODEBUG.
2. C/C++ → Generate codes → Runtime library: Change to multi-thread/MT
Please click on the link and refer to the document located therein.
All our major services are provided in the form of API, SDK, and SaaS, with API and sample codes being directly
integratable with your frontend service. For the ease of development, we also provide documents specifying integration
It is likely that the subject has not been registered. If this message appears when the subject has clearly been registered, please contact admin for help.
It is likely that your face has already been registered. If this message appears when you have not registered your face, please contact admin for help.
Please check if your device is connected to Wi-Fi. The error message appears when the internet connection is lost.
Please contact Alchera's help desk support.
The verification server uses http. Verification can fail if you only accept https.
It is likely that you are trying to use a deactivated key or that your device is not connected to the network.
If there are numerous threads running in the background, this may cause face recognition to slow down. Please restart the application.
The rate for successful recognition can be low if the subject is wearing a hat or sunglasses. Please take the items off and try again. If it still does not work as intended, please try to register your face again.
You can change the settings by clicking on a 'going to'/'leaving work' button on the initial screen of the application.
This can happen when you have a standalone device. Please turn off the application and restart it after a few seconds.
This is most likely to be a problem with incorrect door settings. Please check your door's safety settings.
You have to input the time and press Enter key on your keyboard. If you want to input multiple times, you have to press the Enter key for each time you have input the digits.
This is most likely due to a network problem. Please check if your device has a strong connection to the network and try again. If it is not a network problem, please try deleting and re-installing the application.
The icon for admin mode is hidden so that only admins have access to the page. Please click on the top right corner of the face recognition screen and input your admin password.
The password to access the admin page is 210722.
Notifications can be given anywhere through our web dashboard, text and/or email. You can register as many mobile numbers or email addresses as you want, and view the fire information via the FireScout login provided.
Not currently. However, the FireScout team is constantly discussing and developing opportunities for product expansion. Please contact us with any related inquiries.
FireScout provides features such as ‘Fire Direction’ information, which gives an azimuth and compass reading from the camera location, a ‘History’ tab that lets you see all events that have occurred in a particular date range, and a ‘Review Events’ tab where you can search by camera, for example. The FireScout team is constantly working with first responders and their wildfire stakeholders to further develop and integrate our product features.
Yes. You can download it from the ‘Review Events’ tab.
In most cases, FireScout receives image data every 10 seconds. FireScout can process real-time data if it is available.
We are confident that our FireScout Wildfire Detection AI provides the fastest smoke detection and functions. As a trusted partner of ALERT Wildfire, the world leaders in ground-based wildfire detection camera networks, FireScout has been trained using 10 million + images and is in a constant state of growth and evolution. We are proud to say that FireScout's performance has given us the ability to provide our services to a number of counties, corporations, and government officials, and to continuously develop FireScout with direct experience and feedback from emergency service professionals.
For you, it is now easier than ever to receive product updates and performance improvements. In fact, it's a lot like updating your mobile app, but easier, without any need for such actions like downloading or installing!
The Sacramento River Fire on August 4, 2021 was detected in under 1 minute right from the very first visible puff of smoke, and 1 minute earlier than reported 911 calls. “Alchera's AI had a positive hit within a minute or so of the fire starting. Another minute later, it was called in and put on IRWIN, which then took another 8 minutes for the camera to be moved... positive news across the board, apart from it being a really bad fire,” Dr. Graham Kent of ALERT Wildfire speaking about the River Fire.
Yes, FireScout provides wildfire detection 24/7/365, the only wildfire detection solution that provides this capability.
As a SaaS product, we provide a monthly payment per camera approach. Please inquire for more detailed pricing information.
FireScout is deployed over the ALERT Wildfire network of pan-tilt-zoom AXIS cameras across the Western United States region and Australia.
Yes. If the image data can be uploaded to AWS or any other cloud server, it can be processed by FireScout. Some additional training may be needed though. ALERT Wildfire is our primary camera provider.
In order to provide a consistent 360 degree view and monitor for fire ignitions, some cameras are set to rotate. In most cases, a single tower or location will have two cameras - one set to rotate and one that is stationary to be used for further investigation of a detected smoke event.
Yes, if the image data is received in real-time though. Currently, the whole process, ranging from the camera creating the image to FireScout sending an alert, is less than 1 minute, while the AI detection itself happens in milliseconds.
Put simply, FireScout's accuracy rate is 99%. The FireScout team regularly tests and retrains the algorithm to ensure the optimal balance between recall, precision, and false positive rates. FireScout has also demonstrated and deployed an AI model with a false positive rate of 0.000015.
FireScout is a web-based service and is accessible from any modern device (PC, mobile, tablet) and browser.
1. If you already have ALERT Wildfire cameras in your geographic area, no physical software installation is needed. Once we set up your account information you can begin receiving AI notifications within 2 business days.
2. If you would like to install a camera network with FireScout wildfire detection AI capability, please contact us for more information.
Yes, for each event, you can mark them as “Fire”, “Non-Fire” or “Unknown”. FireScout is trained to detect smoke specifically, though emergency service professionals still need to verify the authenticity of the detected smoke event.
One of the primary objectives of the FireScout team is to provide the best user experience possible. As such, we're confident that this product is straightforward and intuitive to use. We have also recently received product feedback from our users, with 87% of respondents saying that our product is ‘Simple to understand at first glance’.