High-performance weak and small target visual tracking system for open complex environment
The high-performance small target visual tracking system, which combines a heavy-duty turntable, visible light and infrared thermal imaging devices with an information processor, solves the problem of detecting and tracking small targets in complex environments, and achieves high-precision target detection and tracking in all weather and full coverage.
Patent Information
- Application Number
- CN202510926198.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2025-05-20
- Filing Date
- 2025-07-07
- Publication Date
- 2025-09-26
AI Technical Summary
In complex environments, existing technologies find it difficult to achieve high-precision and high-robust detection and tracking of small targets. Especially in rainy, foggy, mountainous, and dense forest environments, the detection and tracking system is prone to losing targets, has a high false alarm rate, and has difficulty capturing small-scale target information.
A high-performance small target visual tracking system consisting of a heavy-duty turntable, visible light imaging device, infrared thermal imaging device and information processor, combined with azimuth and pitch control modules, can achieve all-weather, full-coverage multi-dimensional stereo detection and tracking.
It achieves high-precision target detection and tracking in complex environments and low-visibility conditions, reduces false alarm rates, solves the problem of detecting and tracking weak targets, and provides all-weather monitoring protection.
Smart Images

Figure FT_1 
Figure FT_2 
Figure FT_3
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of target visual tracking, and in particular relates to a high-performance small target visual tracking system for open and complex environments. Background Art
[0002] Among the diverse avenues for acquiring information, vision is the most direct and informative channel for humans to perceive the outside world. Unlike radar information, video image information is highly intuitive. As an extension of human vision, visual target detection and tracking systems can filter out interference from video images without human intervention, extract useful information from the video source, track and identify moving targets in video images, and analyze and judge the target's behavior. This allows for a description of the target's behavior and identification of anomalies in the surveillance footage, effectively providing pre-emptive warnings, in-process processing, and post-event evidence collection.
[0003] Capturing, identifying, and tracking small and weak targets, including drones and long-range targets, are key technologies in target detection and tracking systems. The "weak" and "small" of a target represent two different attributes. "Weak" means that the signal-to-noise ratio of the target is too low, making it difficult to detect the target from a single frame of image. In complex tracking scenarios, such as rainy days, foggy days, high mountains, and dense forests, the detection and tracking system can easily lose the correct target and mistake clutter or noise for the target, significantly increasing the false alarm rate. "Small" means that the target is small in scale, that is, the target occupies very few image pixels, making it difficult for conventional detection and tracking systems to capture the shape, size, texture, and other information of the small target, directly leading to the loss of the target, which inevitably increases the possibility of risk.
[0004] To this end, the present invention provides a high-performance small target visual tracking system for open and complex environments, which can achieve high-precision, high-robustness and high-efficiency small target detection and tracking in different complex environments.
[0005] The information disclosed in this background technology section is only intended to enhance understanding of the overall background of the invention and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the Invention
[0006] The purpose of the present invention is to provide a high-performance small target visual tracking system for open and complex environments, so as to realize all-weather, full-coverage, high-precision, and high-robust multi-dimensional stereo detection and tracking tasks in specific complex environmental areas.
[0007] In order to achieve the above object, the present invention provides the following technical solutions: A high-performance small target visual tracking system for open and complex environments, including: Heavy-duty turntable to provide stable mechanical support for high-precision equipment in the system; Azimuth and pitch control and drive module, used to drive the heavy-duty turntable and ensure smooth rotation, realizing horizontal and pitch operations of the heavy-duty turntable; Visible light imaging device for high-resolution, detail-rich target recognition and tracking; Infrared thermal imaging device, used to provide target detection and tracking in all-weather and low-visibility environments; Information processor, used for data exchange with the outside world.
[0008] Preferably, the heavy-duty turntable includes a pitch motor, a pitch reducer, an azimuth motor and an azimuth reducer; the pitch motor is connected to the pitch reducer; and the azimuth motor is connected to the azimuth reducer.
[0009] Preferably, the azimuth and pitch control and drive module consists of an azimuth and pitch control module and a motor drive module, and adopts 256 subdivision control to ensure the smooth rotation of the heavy-duty turntable; the azimuth and pitch control module is used to convert the received Pelco-D instructions into the azimuth and pitch speed information of the heavy-duty turntable, generate corresponding pulses to control the motor drive module, and realize the horizontal and pitch operations of the heavy-duty turntable; the motor drive module adopts an SR8 two-phase stepper motor driver.
[0010] Preferably, the azimuth and pitch control and drive module includes an azimuth drive control board, an azimuth driver, an azimuth limiter, a pitch drive control board, a pitch driver and a pitch limiter; the azimuth drive control board is connected to the azimuth driver and the azimuth limiter; the azimuth driver is connected to the azimuth motor; the pitch drive control board is connected to the pitch driver and the pitch limiter; and the pitch driver is connected to the pitch motor.
[0011] Preferably, the visible light imaging device includes a lens decoding control board, a high-definition telephoto lens and a high-definition camera; the high-definition telephoto lens is connected to the lens decoding control board and is also connected to the high-definition camera via an optical signal; the high-definition camera acquires images and encodes and compresses them into a network video stream for output, which is then transmitted to the storage and transmission processor via the information processor for real-time recording, and then transmitted to the processing and display terminal for decoding and display.
[0012] Preferably, the infrared thermal imaging device includes an infrared decoding control board, a refrigerated infrared thermal imager and a digital video compression encoder; the refrigerated infrared thermal imager is connected to the infrared decoding control board and is also connected to the digital video compression encoder via an AV video signal.
[0013] Preferably, the information processor includes a video tracker, a network data aggregation module and a control data aggregation module; the video tracker is connected to the high-definition camera and the cooled infrared thermal imager respectively through AV video signals; the network data aggregation module is connected to the high-definition camera and the digital video compression encoder respectively through network digital video signals, and is connected to the control data aggregation module and an external host computer through network control signals; the control data aggregation module is connected to the azimuth drive control board, the pitch drive control board, the lens decoding control board, the infrared decoding control board and the video tracker respectively through RS485 control signals.
[0014] Preferably, the information processor exchanges data of the visual tracking system with the outside through the network data aggregation module. The network data aggregation module collects the network video stream of the front end, the servo information and tracking information of the control data aggregation module and sends them to the indoor control console through the network, and sends the servo control commands, video tracking commands and information sent by the indoor control console to the control data aggregation module.
[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) The high-performance small target visual tracking system for open and complex environments of the present invention can realize all-weather, full-coverage, high-precision, and high-robust multi-dimensional stereo detection and tracking tasks in specific complex environmental areas, solving the problems of small targets being difficult to detect, having a high false alarm rate, and having cross-obscuration and changes in the number of targets during the detection and tracking process.
[0016] (2) With the opening of low-altitude airspace and the diversified development of small-sized aircraft, small targets have posed a significant potential threat to civil aviation, key areas, important activities, and even national security. The present invention proposes a high-performance small target visual tracking system for open and complex environments, which can provide important protection for them. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 This is a diagram showing the implementation of tracking and monitoring technology for a high-performance small target visual tracking system; Figure 2 This is a working principle diagram of a high-performance small target visual tracking system; Figure 3 This is a diagram of the working principle of the visible light imaging device. DETAILED DESCRIPTION
[0018] The following is a clear and complete description of the technical solution of the present invention. Obviously, the embodiments described are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.
[0019] Refer to the attached Figure 1-3 , a high-performance small target visual tracking system for open and complex environments, including five modules: heavy-duty turntable, azimuth and pitch control and drive module, visible light imaging device, infrared thermal imaging device, and information processor. The heavy-duty turntable includes a pitch motor, a pitch reducer, an azimuth motor and an azimuth reducer; The azimuth and pitch control and drive module includes an azimuth drive control board, an azimuth drive, an azimuth limiter, a pitch drive control board, a pitch drive and a pitch limiter; The visible light imaging device includes a lens decoding control board, a high-definition telephoto lens and a high-definition camera; The infrared thermal imaging device includes an infrared decoding control board, a cooling type infrared thermal imager and a digital video compression encoder; The information processor includes a video tracker, a network data aggregation module and a control data aggregation module.
[0020] Refer to the attached Figure 2 The connection relationship of each module is as follows: the pitch motor is connected to the pitch reducer and the pitch driver respectively; the azimuth motor is connected to the azimuth reducer and the azimuth driver respectively; the azimuth drive control board is connected to the azimuth driver and the azimuth limiter respectively; the pitch drive control board is connected to the pitch driver and the pitch limiter respectively; the high-definition telephoto lens is connected to the lens decoding control board, and is also connected to the high-definition camera through optical signals; the cooled infrared thermal imager is connected to the infrared decoding control board, and is also connected to the digital video compression encoder and the video tracker through AV video signals; the video tracker is connected to the high-definition camera and the cooled infrared thermal imager through AV video signals; the network data aggregation module is connected to the high-definition camera and the digital video compression encoder through network digital video signals, and is also connected to the control data aggregation module and the external host computer through network control signals; the control data aggregation module is connected to the azimuth drive control board, the pitch drive control board, the lens decoding control board, the infrared decoding control board, and the video tracker through RS485 control signals.
[0021] In this embodiment, the heavy-duty turntable includes a housing, azimuth drive, pitch drive, motor, reducer, power supply, and other components. It provides stable mechanical support for the system's high-precision equipment (such as high-definition cameras, telephoto lenses, and infrared thermal imagers). The heavy-duty turntable's "heavy" design ensures structural stability even under high loads, preventing tracking deviations caused by the weight of the equipment or external conditions (such as strong winds and vibrations). This is particularly crucial in harsh outdoor environments such as the military. To cope with harsh outdoor environments such as high temperatures, salt spray, and strong winds, the turntable's housing is spherical to reduce wind resistance. Based on functional requirements and the need to reduce wind resistance and maintain waterproofing, the housing of the dedicated heavy-duty turntable adopts a spherical, sealed cavity structure.
[0022] This system incorporates practical operational experience and human-machine operability considerations, utilizing a custom-built, dedicated keyboard with shortcut buttons, knobs, and joysticks for common servo and lens control functions. The keyboard primarily controls the visual tracking system and camera front-end, forwarding control through the processing and display terminals. This allows users to better control the visual tracking system and front-end equipment while viewing video images.
[0023] The azimuth and pitch control and drive module is used to drive the heavy-duty turntable and ensure smooth rotation, enabling pan and tilt operations. It primarily consists of a tilt control module and a motor driver module. The control chip utilizes a 32-bit ARM processor with extensive peripheral communication interfaces and microsecond-level data processing speeds, meeting the high-speed, real-time data processing requirements of the servo control system. The tilt control module converts received Pelco-D commands into the turntable's azimuth and pitch velocity information, generating corresponding pulses to control the motor driver module, enabling pan and tilt operations. The motor driver module utilizes the SR8 two-phase stepper motor driver, a cost-effective, microstepping driver designed with a PID current control algorithm. It offers high-speed, high-torque output, low noise, low vibration, and low heat generation, and features overvoltage, undervoltage, phase current, and total current overcurrent protection. The tilt control and drive module utilizes 256-step control to ensure smooth rotation of the heavy-duty turntable.
[0024] The visible light imaging system consists of a high-definition telephoto lens, a high-definition network camera, and a lens decoding control system, providing high-resolution, detailed target recognition and tracking. The high-definition network camera captures images, encodes and compresses them into a network video stream for output. This is then transmitted via an information processor to a storage and transmission processor for real-time recording and then to a processing and display terminal for decoding and display. Users control the high-definition telephoto lens through the processing and display terminal, using zoom commands to monitor near and far targets and focus commands to adjust target clarity.
[0025] Infrared thermal imaging devices are used to detect and track targets in all-weather, low-visibility environments. They primarily utilize a cooled infrared thermal imager, an infrared detector, an optical imaging lens, and an optical scanning system to receive the infrared radiation energy distribution pattern of the target being measured. This pattern is then reflected onto the infrared detector's photosensitive element. The detector then converts the infrared radiation energy into an electrical signal, which is then amplified and converted into a standard video signal.
[0026] The information processor includes a video tracker, a network data aggregation module and a control data aggregation module, which are used to interact with the outside world and exchange data of the visual tracking system with the outside world through the network data aggregation module. The network data aggregation module collects the network video stream of the front end, the servo information and tracking information of the control data aggregation module and sends it to the indoor control console through the network, and sends the servo control commands, video tracking commands and information sent by the indoor control console to the control data aggregation module.
[0027] The video tracker is mainly composed of ARM information processing module, Flash module, DDR3 cache module, clock management module, power management module, multi-information sensor module and wireless communication module.
[0028] The network data aggregation module adopts a self-developed network switching module, which is mainly composed of two parts: the power control module and the network aggregation module. It uses the high-performance Gigabit Ethernet storage and transmission processor chip RTL8370, supports 8-port full-duplex communication, and realizes the network information aggregation and exchange of tracking actuator control information, visible light camera video and infrared thermal imager video.
[0029] The control data aggregation module uses a 32-bit ARM processor from the STM32F4 series, coupled with a W5500 network chip for data transfer and processing. It transmits received network data via the RS485 port to the azimuth drive control board, pitch drive control board, and video tracker. Simultaneously, data received via the RS485 port is sent to the data aggregation module via the network port. The embedded program uses the uCOS III system, ensuring efficient resource allocation and real-time performance. The control data aggregation module receives status feedback from the azimuth and pitch servo angles, visible light and thermal imaging lens status feedback, and target position information processed by the image tracking module. This data is then generated via the W5500 chip and transmitted to the host computer via TCP network packets. The control data aggregation module also receives TCP network control information from the host computer, decodes it, and forwards it to the corresponding servo controllers, enabling data exchange between the front-end pointing device and the host computer.
[0030] It should be noted that the azimuth and pitch control and drive module of this embodiment also includes an azimuth drive system and a pitch drive system. The azimuth drive system consists of an azimuth transmission device, a motor, and contact bearings. Azimuth transmission is achieved using a synchronous belt and planetary reducer. This transmission method offers advantages such as compact size and a high reduction ratio. The azimuth rotation range is 0-360° continuous, with a maximum rotation speed of no less than 40° / s. The motor's output torque is transmitted to the gimbal's horizontal drive system via a toothed synchronous belt. The horizontal drive system's support structure utilizes tapered roller bearings, and the drive shaft and gimbal housing are sealed with lip seals. Therefore, friction losses in the transmission system are primarily caused by the synchronous belt, bearings, and seals.
[0031] According to the mechanical design manual, the transmission efficiency of the synchronous belt is 0.96-0.98; the transmission efficiency of the roller bearing (oil lubrication) is 0.98. Considering the increased bending stress of the synchronous belt and the increased viscosity of the bearing grease when the gimbal operates at low temperatures, the transmission efficiency of the synchronous belt and bearings needs to be appropriately reduced. Assuming the transmission efficiency of the synchronous belt is 0.94, the transmission efficiency of the bearing is 0.96 (single bearing), and the power loss of the sealing structure is 0.05, the estimated transmission efficiency of the entire transmission system is: η=0.94*0.96*0.96*0.95=0.823; Motor output rated speed: Rrated = 500rpm = 3000° / s; Motor output rated torque: Mrated = 8.4Nm; Reducer reduction ratio i=32; Transmission efficiency: η = 0.823; The torque converted to the load shaft is M=Mrated*i*η=8.4*32*0.823=221.2 Nm; Converted to the speed of the load shaft, V=Rrated / i=93° / s; Known: The maximum azimuth speed of the dedicated heavy-duty turntable is ω = 40° / s; the total azimuth load torque is Mtotal = 32.57 Nm; To sum up: M>Mtotal, and V>ω, the azimuth motor reducer selection meets the load requirements.
[0032] On the other hand, the pitch drive system consists of a pitch transmission device, a motor, a contact bearing, etc. The pitch rotation range is -45°±5°~90°±5° continuous rotation, and the maximum rotation speed is not less than 30° / s.
[0033] Pitch load: WL = 60kg; The moment of inertia of the azimuth load is calculated with the pitch axis as the rotation axis: J pitch = 3.4 kg·m2; Maximum pitch angular velocity: ω pitch = 30° / s = 0.523 rad / s; Maximum pitch acceleration: α pitch = 80° / s2 = 1.396 rad / s2; Pitch inertia moment: M pitch = J pitch * α pitch = 3.4 * 1.396 = 4.75 Nm; The torque caused by the external wind load is: Mwind = 13.77 Nm; Friction torque: M = 0.5 Nm; The total moment of the pitching load is: Mtotal = Mwind + Mfriction + Mpitch = 13.77 + 0.5 + 4.75 = 19.02 Nm; Known: The maximum pitch speed of the dedicated heavy-duty turntable is: ω = 30° / s; the total pitch load torque is: Mtotal = 19.02Nm; To sum up: M>Mtotal, and V>ω, the pitch motor reducer selection meets the load requirements.
[0034] The foregoing descriptions of specific exemplary embodiments of the present invention are for purposes of illustration and description. These descriptions are not intended to limit the invention to the precise forms disclosed, and it is apparent that many variations and modifications are possible in light of the foregoing teachings. The exemplary embodiments have been selected and described for the purpose of explaining the specific principles of the invention and their practical application, thereby enabling those skilled in the art to realize and utilize a variety of exemplary embodiments of the invention and various options and modifications. The scope of the invention is intended to be defined by the claims and their equivalents.
Claims
1. A high-performance small target visual tracking system for open and complex environments, characterized by: include: Heavy-duty turntable to provide stable mechanical support for high-precision equipment in the system; Azimuth and pitch control and drive module, used to drive the heavy-duty turntable and ensure smooth rotation, realizing horizontal and pitch operations of the heavy-duty turntable; Visible light imaging device for high-resolution, detail-rich target recognition and tracking; Infrared thermal imaging device, used to provide target detection and tracking in all-weather and low-visibility environments; Information processor, used for data exchange with the outside world.
2. The high-performance small target visual tracking system for open and complex environments according to claim 1 is characterized in that: The heavy-duty turntable includes a pitch motor, a pitch reducer, an azimuth motor and an azimuth reducer; the pitch motor is connected to the pitch reducer; and the azimuth motor is connected to the azimuth reducer.
3. The high-performance small target visual tracking system for open and complex environments according to claim 2 is characterized in that: The azimuth and pitch control and drive module consists of an azimuth and pitch control module and a motor drive module, and adopts 256 subdivision control to ensure the smooth rotation of the heavy-duty turntable; the azimuth and pitch control module is used to convert the received Pelco-D instructions into the azimuth and pitch speed information of the heavy-duty turntable, generate corresponding pulses to control the motor drive module, and realize the horizontal and pitch operations of the heavy-duty turntable; the motor drive module adopts an SR8 two-phase stepper motor driver.
4. The high-performance small target visual tracking system for open and complex environments according to claim 3 is characterized in that: The azimuth and pitch control and drive module includes an azimuth drive control board, an azimuth driver, an azimuth limiter, a pitch drive control board, a pitch driver and a pitch limiter; the azimuth drive control board is connected to the azimuth driver and the azimuth limiter; The azimuth driver is connected to the azimuth motor; the pitch drive control board is connected to the pitch driver and the pitch limiter; The pitch driver is connected to the pitch motor.
5. The high-performance small target visual tracking system for open and complex environments according to claim 4 is characterized in that: The visible light imaging device includes a lens decoding control board, a high-definition telephoto lens and a high-definition camera; the high-definition telephoto lens is connected to the lens decoding control board and is also connected to the high-definition camera via an optical signal; the high-definition camera collects images, encodes and compresses them into a network video stream for output, transmits them to the storage and transmission processor through the information processor for real-time recording, and then transmits them to the processing and display terminal for decoding and display.
6. The high-performance small target visual tracking system for open and complex environments according to claim 5 is characterized in that: The infrared thermal imaging device includes an infrared decoding control board, a refrigerated infrared thermal imager and a digital video compression encoder; the refrigerated infrared thermal imager is connected to the infrared decoding control board and is also connected to the digital video compression encoder via an AV video signal.
7. The high-performance small target visual tracking system for open and complex environments according to claim 6 is characterized in that: The information processor includes a video tracker, a network data aggregation module and a control data aggregation module; the video tracker is connected to the high-definition camera and the refrigerated infrared thermal imager respectively through AV video signals; the network data aggregation module is connected to the high-definition camera and the digital video compression encoder respectively through network digital video signals, and is connected to the control data aggregation module and an external host computer through network control signals; the control data aggregation module is connected to the azimuth drive control board, the pitch drive control board, the lens decoding control board, the infrared decoding control board and the video tracker respectively through RS485 control signals.
8. The high-performance small target visual tracking system for open and complex environments according to claim 7 is characterized in that: The information processor exchanges data of the visual tracking system with the outside through the network data aggregation module. The network data aggregation module sends the network video stream of the acquisition front end, the servo information and tracking information of the control data aggregation module to the indoor control console through the network, and sends the servo control commands, video tracking commands and information sent by the indoor control console to the control data aggregation module.