Object Detection and Tracking
Scylla AI-powered proprietary object detection and classification engine augments your security infrastructure and provides situational awareness in real-time.
Book a demoRelated materials
Key Steps in Active Shooter Preparedness for Businesses
Enhancing active shooter preparedness is a must for all organizations. Learn which steps businesses must take to improve active shooter response and physical security.
Read more
Interview with Oliver Schneider
In the interview, an ex-commando officer and a risk and crisis management consultant, Oliver Schneider, speaks about his exciting experience and collaboration with Scylla.
Read more
Advantages of Using Artificial Intelligence in Video Surveillance
AI video analytics has gained immense popularity over the past couple of years due to a large number of real-world use cases. Learn about the actual advantages of leveraging AI-powered face recognition, object and intrusion detection solutions for security purposes.
Read moreFAQ
Yes, the models are trained on a wide variety of sceneries and backgrounds, under versatile illumination and views. Essentially the solution is agnostic towards the background – as long as the object of interest is visible, the system is bound to detect it.
The answer to this question depends on a number of factors. To begin with, it relies on the camera characteristics and the resolution, in particular. A resolution initially plays a big role, however, the incorporated zooming-tracking algorithm Scylla uses allows checking the object in the original resolution the camera uses. Thus, unlike similar AI security solutions, Scylla is not heavily dependent on the quality of the visuals that are usually downgraded when processed through neural network platforms. Then there is a group of characteristics that can be related to camera “picture quality”, such as stream bandwidth, encoding, etc. There are conditions of visibility to consider as well, such as the illumination, position (see Question 6 on object angle), and the pixel size of the object. The latter linearly depends on the distance from the camera and can be used for distance limit estimates. For example, the reliable minimum size limit for a gun object is around ~15-17 pixels which results in a maximum distance of up to 10-12 meters for most HD cameras.
The detection typically happens in the first 400 ms (in some cases, up to 2 seconds). When assessing the response time, take into account that most IP cameras used nowadays show some sub-second lag of the video stream. Also in the cases when Scylla is deployed on the cloud, one has to take into consideration the time lag that takes place when the stream reaches the cloud and the response reaches the dashboard.
Scylla Object Detection System is designed to help security units by supporting their daily operations, augmenting their capabilities, and eliminating possible human factor related flaws. Also, in case of a possible threat, the alert that is sent out by Scylla is enriched with information crucial for the quick and inclusive analysis of the threat on-site and effective planning of dedicated counteractions.
The system is based on computer vision algorithms and detection of the threat is based on visual content analysis. This means that to detect a weapon in a bag Scylla has to be attached to X-Ray or millimeter-wave scanning devices. Running on CCTV cameras that operate in visual range only, Scylla Object Detection can detect only non-concealed weapons.
No, the system is trained on all possible angles of objects of interest. Of course, in some specific cases, the angle of the object would matter as the features that Scylla uses to classify the object are more distinct in some angles than others. For instance, if a gun/rifle is held at an angle towards the camera, more distinct features are visible compared to the cases when they are pointed directly at the camera.
An alert containing all the crucial information is compiled and delivered to end-users responsible for security. There is a number of customizable alerting pathways: Scylla dashboard, Scylla mobile alerting application, access point relay boards, and VMS alerting API, to name a few.
The limit here is only the hardware that runs Scylla AI video analytics. More specifically, the main deciding characteristics are GPUs the servers are equipped with. Other than that, Scylla can simultaneously accept video streams from different cameras with different characteristics.
Yes, all solutions provided by Scylla can be deployed both on the cloud and on-premise. Moreover, Scylla AI-powered security software solutions are agnostic towards the cloud provider, as long as the cloud instance runs Linux and is equipped with an Nvidia GPU card.
Yes, it can. The maximum detection distance of Scylla Object Detection Solution will depend on the camera characteristics (contrast ratio, pixel crosstalk, etc.). But in general, the solution complies with industry-standard DRI requirements. i.e. the identification limit (the distance at which you can determine the class of an object) is ~20 pixels for small weapons.
An alert is classified as a true alarm when the prediction of AI corresponds to reality (i.e. the object of interest is correctly identified, the action sought after is detected, etc.). A false positive is a case when the alert is triggered by mistake. Unfortunately, due to the essentially probabilistic nature of AI, the latter are inevitable in most cases. However, due to the elaborate AI and machine learning behind Scylla Object Detection System, it can meet any level of production-grade industrial standards. Moreover, we are continuously improving Scylla AI video analytics modules where they are retrained on mistakes to make sure the number of false alarms goes even further down with time.
Scylla Object Detection System is essentially camera make-agnostic. Most questions on the limitations and camera requirements end up receiving a simplified “rule-of-thumb” answer — if a human can see and identify the object of interest, then Scylla AI video analytics will also be able to do that (and in some cases, will even outperform a human due to the integrated zooming and re-checking algorithms). As for the minimal camera parameters, these will depend on each use case and the object of interest you are trying to detect. Of course, the camera should have a digital output or at least be connected to a DVR that has one. Scylla Object Detection System can accept pretty much all the variety of stream types, such as RTSP/RTMP, HTTP, etc. Usually, the minimum required resolution starts from HD (1280x720) and 5 FPS. Parameters defining the frame/image quality vary from one camera to another, but we recommend looking into such characteristics as bandwidth, encoding, and sharpness, and improving them if necessary.
Absolutely. Scylla does not store any information (unless requested specifically by the user).
The duration of alerts depends on the client's data retention policy. By default, we offer a storage duration of one month, but this period can be configured to correspond to local policies.
Yes, it can. Scylla’s computer vision engine is indifferent to moving and changing backgrounds and works similar to human vision - if the object is there and it is distinguishable, Scylla spots it and reports. Of course, the blurring of objects during PTZ shifts should be taken into account.
Scylla Object Detection System is designed to work in challenging environments where cameras with embedded algorithms do not perform well. The AI engine compensates for the drawbacks imposed by demanding conditions including but not limited to poor illumination, somewhat corrupted frames, environmental factors, and weather-foisted effects.
Scylla Object Detection System is not designed to detect unhandled or hosted weapons. It triggers the alert as soon as the weapon is in possession of a human.