English
 |
| PDF Export | |
IAS100
• Enhanced moving target detection: support the use of target recognition, target tracking to enhance the movement of the minimum and maximum target detection, trip line detection and area intrusion detection;
• Human Motion Diversity Detection: support human body in squat, walk, run, jump, crawl, swimming and other movements of the maximum and minimum target detection;
• A variety of target detection: support detection of people, vehicles, ships, animals, birds, unmanned aircraft, airborne objects, aircraft, landing gear and other targets;
• Dual-light video detection: Support Visible Light, thermal imaging video synchronization rules, synchronization asynchronous rules, error synchronization rules and error-time different rules detection mode;
• Long-distance small target: support the intrusion alarm detection to the small target under 5 * 5 pixels; support the detection and recognition to the super small target under 15 * 15 pixels;
• Cloud Edge multi-form deployment: support the overall system solution to achieve software + algorithm business integration; support the back-end algorithm analysis platform, intelligent algorithm analysis suite and algorithm model authorization cooperation.
Model | IAS100 AI algorithm video analysis Software | |
Applicable Equipment | Photo-electric turntable, photo-electric head, electronic sentry, Universal Security Camera | |
System Performance | Single service supports no less than 16 channels of video real-time detection (the specific number is limited by the hardware configuration) Single service supports no less than 100 channels of video time-sharing detection (the number of channels is limited by hardware configuration) | |
Image Analysis | 1. Target tracking: support single target and multi-target tracking algorithm, real-time display of target trajectory; Support automatic tracking of target recognition (optional) , automatic tracking of target intrusion area, automatic tracking of target collision line, manual selection of target tracking, recognition of tracking target algorithm (optional) , automatic doubling of tracking process, automatic recovery of target loss; Support for water, land and air scene target tracking, support KCF, optical flow tracking algorithm; Support visible light video tracking, thermal imaging video tracking, turntable device angular velocity tracking and PID tracking, platform device velocity class tracking 2. Panoramic stitching: support visible light panoramic stitching, thermal imaging panoramic stitching; support level 360 ° , pitch ≥50 ° seamless panoramic stitching; support panoramic upload, download function 3. Semantic segmentation: support visual video semantic segmentation, thermal imaging video semantic segmentation; support semantic segmentation based on deeplabv3 series, based on DNANet target segmentation model; Support for people, vehicles, ships, drones, animals and other objects, such as the pixel-level segmentation; support the separation of the sky and the ground, small targets and clutter background separation 4. Moving Target Detection: support moving target detection, target stir line detection, area intrusion detection; It supports motion detection, trip detection and area intrusion detection of minimum and maximum targets by means of target recognition (optional) and target tracking Support visible video moving target detection, thermal imaging video moving target detection, real-time display of moving target trajectory | |
Moving Object Detection Capability | Visible Light 1080P resolution to support the detection of no less than 5 * 5 pixels of the target | |
Thermal imaging supports detection of objects not less than 3 x 3 pixels at D1 resolution | ||
after the enhancement, the detection accuracy reaches above 95% | ||
Video Processing | 1. Pull-stream decoding: support for video decoding of device direct-connected and streaming media forwarding and fetching, support for decoding, clipping and compression of common video resolution such as 1080P, 1280 * 1024,720P, D1,640 * 512, etc. Support one decoding for multi-model, multi-algorithm synchronization 2. Video Coding: support decoding video and reasoning information fusion coding; support coding video compression, video service release and directional push 3. Inference Playback: support video frame model reasoning, target marking, occlusion, attribute extraction, target information storage, inference video storage and target alarm push; The system supports 1 frame/NS as well as 25 frames/s inference frame rate control, inference record, video query, playback and download 4. Model Management: Support Model Upload, DELETE, upgrade and other management operations; support add, Delete, browse, rename, hidden and other reasoning tag management operations; Support multi-process, multi-model algorithm scheduling, support manual upload video, picture test algorithm model reasoning effect | |
Hardware adaptation | 1. Support the Hayes chip, Atlas, Cambrian, Nvidia and other types of chips, GPU algorithm transfer and adaptation 2. Support for cloud, edge, end-form deployment; support for back-end services distributed networking, Edge intelligent 1 + N detection and end-to-side small model migration adaptation | |
Interface Protocol | 1. Access Protocol: RTSP, GB28181(optional) video access protocol; support the mainstream manufacturers such as haikang, Dahua, Yushi Access Protocol 2. Secondary development: support SDK secondary development, support Restful API platform docking, support to provide RTSP format reasoning video stream | |
※ The system application is related to the protocol and functional characteristics of the camera equipment, the system performance and the hardware resources of the operating environment, please contact us according to the actual situation.
• Enhanced moving target detection: support the use of target recognition, target tracking to enhance the movement of the minimum and maximum target detection, trip line detection and area intrusion detection;
• Human Motion Diversity Detection: support human body in squat, walk, run, jump, crawl, swimming and other movements of the maximum and minimum target detection;
• A variety of target detection: support detection of people, vehicles, ships, animals, birds, unmanned aircraft, airborne objects, aircraft, landing gear and other targets;
• Dual-light video detection: Support Visible Light, thermal imaging video synchronization rules, synchronization asynchronous rules, error synchronization rules and error-time different rules detection mode;
• Long-distance small target: support the intrusion alarm detection to the small target under 5 * 5 pixels; support the detection and recognition to the super small target under 15 * 15 pixels;
• Cloud Edge multi-form deployment: support the overall system solution to achieve software + algorithm business integration; support the back-end algorithm analysis platform, intelligent algorithm analysis suite and algorithm model authorization cooperation.
Model | IAS100 AI algorithm video analysis Software | |
Applicable Equipment | Photo-electric turntable, photo-electric head, electronic sentry, Universal Security Camera | |
System Performance | Single service supports no less than 16 channels of video real-time detection (the specific number is limited by the hardware configuration) Single service supports no less than 100 channels of video time-sharing detection (the number of channels is limited by hardware configuration) | |
Image Analysis | 1. Target tracking: support single target and multi-target tracking algorithm, real-time display of target trajectory; Support automatic tracking of target recognition (optional) , automatic tracking of target intrusion area, automatic tracking of target collision line, manual selection of target tracking, recognition of tracking target algorithm (optional) , automatic doubling of tracking process, automatic recovery of target loss; Support for water, land and air scene target tracking, support KCF, optical flow tracking algorithm; Support visible light video tracking, thermal imaging video tracking, turntable device angular velocity tracking and PID tracking, platform device velocity class tracking 2. Panoramic stitching: support visible light panoramic stitching, thermal imaging panoramic stitching; support level 360 ° , pitch ≥50 ° seamless panoramic stitching; support panoramic upload, download function 3. Semantic segmentation: support visual video semantic segmentation, thermal imaging video semantic segmentation; support semantic segmentation based on deeplabv3 series, based on DNANet target segmentation model; Support for people, vehicles, ships, drones, animals and other objects, such as the pixel-level segmentation; support the separation of the sky and the ground, small targets and clutter background separation 4. Moving Target Detection: support moving target detection, target stir line detection, area intrusion detection; It supports motion detection, trip detection and area intrusion detection of minimum and maximum targets by means of target recognition (optional) and target tracking Support visible video moving target detection, thermal imaging video moving target detection, real-time display of moving target trajectory | |
Moving Object Detection Capability | Visible Light 1080P resolution to support the detection of no less than 5 * 5 pixels of the target | |
Thermal imaging supports detection of objects not less than 3 x 3 pixels at D1 resolution | ||
after the enhancement, the detection accuracy reaches above 95% | ||
Video Processing | 1. Pull-stream decoding: support for video decoding of device direct-connected and streaming media forwarding and fetching, support for decoding, clipping and compression of common video resolution such as 1080P, 1280 * 1024,720P, D1,640 * 512, etc. Support one decoding for multi-model, multi-algorithm synchronization 2. Video Coding: support decoding video and reasoning information fusion coding; support coding video compression, video service release and directional push 3. Inference Playback: support video frame model reasoning, target marking, occlusion, attribute extraction, target information storage, inference video storage and target alarm push; The system supports 1 frame/NS as well as 25 frames/s inference frame rate control, inference record, video query, playback and download 4. Model Management: Support Model Upload, DELETE, upgrade and other management operations; support add, Delete, browse, rename, hidden and other reasoning tag management operations; Support multi-process, multi-model algorithm scheduling, support manual upload video, picture test algorithm model reasoning effect | |
Hardware adaptation | 1. Support the Hayes chip, Atlas, Cambrian, Nvidia and other types of chips, GPU algorithm transfer and adaptation 2. Support for cloud, edge, end-form deployment; support for back-end services distributed networking, Edge intelligent 1 + N detection and end-to-side small model migration adaptation | |
Interface Protocol | 1. Access Protocol: RTSP, GB28181(optional) video access protocol; support the mainstream manufacturers such as haikang, Dahua, Yushi Access Protocol 2. Secondary development: support SDK secondary development, support Restful API platform docking, support to provide RTSP format reasoning video stream | |
※ The system application is related to the protocol and functional characteristics of the camera equipment, the system performance and the hardware resources of the operating environment, please contact us according to the actual situation.
