Dragon boat paddle frequency and strength balance testing device and method in use scene

Abstract

The invention relates to a dragon boat paddle frequency and strength balance testing device and method in a use scenario, the testing device comprises a water area and a shore part, the water area comprises multiple sets of grip strength detection devices, multiple sets of sound insulation headsets, a Beidou satellite positioning module arranged on the dragon head of each dragon boat, a dragon ball arranged on the dragon gap and a fireball arranged on the dragon tail, respectively serving as markers. The shore part comprises camera devices arranged on shores at the two ends of a channel where each dragon boat is located, and a PC arranged on the left shore in the standard vertical direction serves as a background server. The whole dragon boat paddling process is coordinated, the paddling action of a paddler is dynamically adjusted, and real-time synchronous movement of the dragon boat in a real site is achieved.

Description

Technical Field

[0001] The present invention relates to a paddle frequency and force balance test device and method, particularly to the paddle frequency and force balance test under actual use scenarios of dragon boats, belonging to the field of sports equipment testing. Background Art

[0002] Paddle frequency and force balance are important indicators in dragon boat races, which are related to the race results and can help to discover the direction of training efforts in a timely review. The training of these two indicators for existing dragon boats is based on simulators, and sensors are installed on the pool wall. However, in actual races, due to on-site performance, athletes' psychology, the quality of usual training, the training status in the days before the competition, weather and other reasons, the actual on-site indicators are affected and cannot be linearly compared with the training on the simulator usually. That is to say, the training on the simulator cannot truly reflect the training with a dragon boat, especially the accurate comparison of the on-site state during the race. Moreover, it is impossible to lay sensors over a long distance within cost control for the movement of the dragon boat, and the water area on-site is wide, so it is also impossible to exclude the precise calculation of the water surface wave noise and the wave energy attenuation caused by paddling.

[0003] In addition, in order to adapt to the competition site, training on the "real boat" is the best solution. Therefore, it is particularly important to set up a dragon boat paddle frequency and force balance test device and a test method on the real boat on-site. Summary of the Invention

[0004] Due to the above unsolved problems in the prior art, the following several solutions are adopted in the design of the present invention. First, a grip force detection device suitable for paddling is set up. Second, camera devices are set at both ends of each track to record the time-varying state of the grip force and the image of the boat body, corresponding to the paddle frequency, synchronization, and the relationship with the force balance result respectively. Third, sound-insulating earphones are configured for the paddlers to prompt each paddler whether to pay attention to the speed of the paddle frequency according to the prediction of the force balance result.

[0005] Based on the above design solutions, the present invention provides a dragon boat paddle frequency and force balance test device under actual use scenarios, including: grip force detection devices with the same quantity as the number of dragon boat paddles, which are used to monitor the change function of the pressure generated by the fingers holding the paddle surface over time, so as to calculate the paddle frequency of each paddler; camera devices set at both ends of the track; markers set at both the head and the tail of the dragon boat, which are used to calculate the yaw degree of the boat body according to the video or multiple images taken by the camera devices, and build a model to predict the force balance result through the historical grip force data of each paddler and the calculation result of the yaw degree, and also include sound-insulating earphones worn by the paddlers, a satellite positioning module set on the dragon head, and a background server on the shore of the water area, wherein, The grip force detection device, camera device, soundproof earphone, and satellite positioning module are all in communication with the background server, uploading and saving the variation function, video, or multiple images to the background server, performing the calculation and constructing a model to predict the force balance result in the background server, and sending a prompt message to the soundproof earphone worn by the paddler.

[0006] Optionally, the paddle rod of the paddle has a grip force detection part for installing the grip force detection device. The grip force detection device includes a flexible substrate, with a pressure sensing sheet on one side and an acquisition amplifier electrically connected to the pressure sensing sheet on the other side, for collecting and amplifying the pressure signal of the grip force, and sending it to the background server through the antenna hole with an antenna arranged on the paddle rod via a wireless transmission module electrically connected thereto; the method for calculating the paddle frequency of each paddler is to find the time interval between two adjacent peaks in the variation function. , then the paddle frequency .

[0007] It should be understood that the paddling action determines that the fingers corresponding to the main paddling arm need to exert pressure on the surface of the paddle rod when paddling out to overcome the water pressure on the paddle blade, and then when the paddle blade leaves the water and the palm pushes the paddle rod forward in front of the body, the pressure of the fingers corresponding to the main paddling arm on the paddle rod decreases. In this way, a periodic pattern is formed in the time variation function, and thus the paddle frequency is calculated.

[0008] Preferably, all the soundproof earphones can be controlled by the background server to play the work songs synchronously to coordinate the paddling rhythms of all paddlers.

[0009] Optionally, the calculation method of the yaw degree includes: S1. The background server receives the position of the dragon head sent by the satellite positioning module in real time, and obtains the real-time distance between it and the dragon head according to the position of the camera device set in front of the dragon head outside the water area. , and according to the distance between it and the camera device set behind the dragon tail outside the water area. , and the distance between the dragon head and dragon tail markers. , calculate the distance between the marker set at the dragon tail and the camera device set behind the dragon tail outside the water area as ; S2. Obtain the current video frame or the captured image, and respectively calculate the principal distances and of the cameras set in front of the dragon head and behind the dragon tail outside the water area, and the lateral distances and of the markers set at the dragon head and dragon tail from the crosshair in the field of view, and calculate the lateral distances and of the dragon head and dragon tail deviating from the standard direction., where the crosshairs are on the line connecting the projections on the sensing surfaces of each photographic device, and the direction towards the forward movement of the boat body is defined as the standard direction; S3 Yaw degree .

[0010] Preferably, , then .

[0011] Optionally, the method for constructing a model to predict the force balance result through the grip force historical data of each rower and the calculation result of the yaw degree specifically includes: Q1 Construct a long short-term memory network. For each rower, divide the grip force historical data into a training set and a validation set in proportion, and sequentially input the training set into each node unit of the network constructed in chronological order. The output end outputs the current unit's paddle frequency, which is compared with the true value to obtain the corresponding loss function. Each node unit corresponds to at least one rowing action, and the first node unit also inputs an initial signal (usually the background signal of the pressure sensor) at the transmission layer; Q2 Use the validation set to verify the accuracy rate and optimize the network parameters using the loss function. Continuously alternate such training and verification until the loss function is minimized and the accuracy rate stabilizes, completing the training; Q3 Obtain the yaw degree data at the current moment, input the grip force detection data of all rowers at the current moment into the node unit of the trained network corresponding to the rower, and output the predicted paddle frequency , is the rower number. When , , then for the rowers on the left side of the forward direction, among those with the predicted paddle frequency persons, is the true paddle frequency of the rower numbered at the current moment (i.e., obtained from the time interval between the peak signal intensities during two consecutive rowing processes at the current moment and the previous moment). The background server sends a prompt message to their soundproof earphones to pay attention to appropriately increasing the paddle frequency. For persons, a prompt message to pay attention to appropriately reducing the paddle frequency is sent, and for no prompt message is sent; when , then similarly, for the rowers on the right side of the forward direction, corresponding prompt messages for reducing or increasing the paddle frequency are sent, or no prompt message is sent; Q4 After a preset time, obtain new yaw degree data again. If , then give the prediction result of the force balance. Otherwise, continue to execute Q3 - Q4 until is satisfied.

[0012] It is easy to understand that the yaw of the boat body to one side is caused by a rower on the other side of the boat body opposite to that side having a simply too fast or too slow oar frequency, or both too fast and too slow oar frequencies existing simultaneously, especially those near the dragon head being too fast and those near the dragon tail being too slow. Therefore, it is necessary to determine whether to send a prompt message to increase or decrease based on the relationship between the predicted oar frequency and the measured oar. Among them, the prediction of force balance is based on satisfying on the premise that it is still highly probable to remain satisfied at the next moment for the prediction. Due to the adjustment of the oar frequency and the correction of the yaw degree of the boat body, it takes a certain amount of time. Therefore, the force is predicted to be balanced within a short period of time.

[0013] Preferably, once is satisfied, a prompt message to maintain the oar frequency is immediately sent to the sound-insulating earphone of the rower being prompted. If the condition of still cannot be achieved after two consecutive executions of Q3, the volume of the chant is controlled to increase to coordinate the oar frequencies of all rowers.

[0014] Preferably, the preset time is 3 - 10s.

[0015] Optionally, the background server includes at least one of a PC, a laptop, and a tablet computer.

[0016] On the other hand, the present invention provides a method for testing the oar frequency and force balance of a dragon boat in a use scenario. The method uses the aforementioned testing device and specifically includes the following steps: P1 According to the water area size, multiple channels are set, and camera devices are set on the shores at both ends of each channel. Each dragon boat is positioned at the starting position, and the background server obtains the position information of the satellite positioning module on each dragon head. P2 All rowers wear sound-insulating earphones. Hearing the starting command sent by the background server, each dragon boat starts to move forward. The background server immediately obtains the position information of the satellite positioning module, the collected video frames and images of the camera device on the shore corresponding to the channel, and the grip force detection data corresponding to all rowers to calculate the oar frequency based on the grip force detection data. P3 Calculate the yaw degree of the boat body based on the collected video frames and images, and predict the force balance result through the grip force detection data of each rower and the calculation result of the yaw degree, and send a prompt message to the sound-insulating earphone worn by the rower accordingly.

[0017] Beneficial effects By applying pressure to the oar shaft with the gripping hand, the shore-based photographic device captures the deviation of the dragon head and dragon tail markers from the field of view reticle, constructs a model to predict the stroke rate and force balance results, and uses a back-end server to coordinate the entire dragon boat rowing process. At the same time, a soundproof microphone is worn to prompt the rowers' stroke rate based on the force balance results, solving the problem of dynamically adjusting the rowing actions of the rowers and simultaneously playing the work songs to coordinate with the rowers, achieving real-time synchronous movement in the real dragon boat scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the part of the dragon boat stroke rate and force balance test device configured in the water under the usage scenario of Embodiment 1 of the present invention. Among them, the posture of the rower wearing a soundproof earphone in the dragon boat holding the oar to row the water is shown.

[0019] Figure 2 For Figure 1 The setting position of the grip force detection part marked by the dotted line in the middle during rowing, and the schematic diagram of the structure of the grip force detection device. Figure 3 Schematic diagram of the force analysis of the gripping hand of the main rowing arm during rowing. Figure 4 Schematic diagram of the part of the dragon boat stroke rate and force balance test device configured on the shore under the usage scenario of Embodiment 1 of the present invention. Among them, the definitions of each distance are shown, as well as the field of view schematic diagram of the camera devices set on the shore corresponding to the head and tail, with a cross reticle. Figure 5 Schematic diagram of the function of grip force changing with time, which shows the period, that is, the time interval between two peaks. , Figure 6 Schematic diagram of the process of using the grip force historical data to train a long short-term memory network to obtain the predicted stroke rate in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] Embodiment 1 As Figures 1 - 4 shown, this embodiment will describe the dragon boat stroke rate and force balance test device under the usage scenario, which is divided into the part in the water and the part on the shore. Specifically, there are 8 sets of grip force detection devices in the water ( Figure 2 ), 8 sets of soundproof earphones ( Figure 1 , only one set is shown exemplarily in the figure), Beidou satellite positioning modules set on the dragon heads of 8 dragon boats ( Figure 1 not shown in the figure), the dragon ball set at the dragon's mouth, that is, marker A, and the fireball set at the dragon's tail, that is, marker B (see Figure 1 ); The part on the shore includes camera devices set on the shore at both ends of the lane where each dragon boat is located ( Figure 4, a total of two, specifically, high-definition cameras with long lenses can be selected, equipped with video, image acquisition, and wireless transmitters), and a PC computer set on the left side of the shore in the standard vertical direction is used as the background server ( Figure 4 ). In this embodiment, the main focal lengths of the two high-definition cameras are the same, both being .

[0021] The PC computer communicates with the grip force detection device, soundproof earphones, Beidou satellite positioning module, and imaging device.

[0022] As Figure 1 shown, an oarsman is exemplarily given, and a virtual circle is drawn around the hand corresponding to the main rowing arm. The enlarged part is shown in Figure 2 , which is the grip force detection part for installing the grip force detection device. The grip force detection device is shown in the enlarged view guided by the two dotted lines of the grip force detection part. Specifically, it includes a flexible substrate (such as silica gel), with a pressure sensing sheet on one side and an acquisition amplifier electrically connected to the pressure sensing sheet on the other side, which is used to collect and amplify the pressure signal of the grip force, and through the wireless transmission module electrically connected to it, it is sent to the background server via the antenna hole with an antenna set on the oar shaft (see Figure 2 ); the method for calculating the stroke rate of each oarsman is to find the time interval between two adjacent peaks on the variation function , then the stroke rate .

[0023] As Figure 3 shown, when the hand corresponding to the main rowing arm holds the oar shaft and rows towards the water, Figure 2 the oar blade in Figure 5 receives water resistance, then the four fingers generate a resistance pressure perpendicular to the surface of the pressure sensing sheet on the surface of the grip force detection part as shown in the figure. And when the oar blade emerges from the water surface, the holding hand pushes forward towards the body, and the pressure generated at this time decreases. Thus, there is a signal intensity peak time interval between two slides with a period as shown in

[0024] , and the stroke rate is calculated from the above formula. Figure 4 Among them, as shown, the distance between the lens of the imaging device on the shore near the head of the dragon and the marker A is expressed as , the distance between marker A and marker B is , and the lens distance between the two imaging devices at both ends of the head and tail of the dragon is and . A crosshair is set in the lens field of view. As shown in the figure, the distances between marker A and marker B and the crosshair in the field of view of the head and tail lenses have lateral deviations (that is, both are to the right of the projection of the standard direction on the sensing surface) of

[0025] The test device can calculate the yaw degree of the boat body based on multiple images captured by the camera device, and construct a model to predict the force balance result through the grip force historical data of each rower and the calculation result of the yaw degree.

[0026] Embodiment 2 This embodiment will illustrate the calculation and prediction model construction in Embodiment 1.

[0027] Specifically, the calculation method of the yaw degree includes: S1. The onshore PC computer uses a server-level host to receive the position of the dragon head sent by the Beidou satellite positioning module in real time, and obtains its real-time distance from the dragon head according to the position of the camera device set in front of the dragon head outside the water area. , and according to its distance from the camera device set behind the dragon tail outside the water area , as well as the distance between the markers at the dragon head and the dragon tail , calculate the distance between the marker set at the dragon tail and the camera device set behind the dragon tail outside the water area as ; S2. Obtain the currently captured image, and respectively calculate the principal distance of the cameras of the camera devices set in front of the dragon head and behind the dragon tail outside the water area , as well as the horizontal distances of the markers set at the dragon head and the dragon tail from the crosshair in the field of view and ( Figure 4 ), calculate the horizontal distances of the dragon head and the dragon tail deviating from the standard direction as and , where the crosshair is on the connection line of the projections on the sensing surfaces of each camera device, and the direction towards the forward movement of the boat body is defined as the standard direction; S3. The yaw degree .

[0028] Constructing a model to predict the force balance result through the grip force historical data of each rower and the calculation result of the yaw degree specifically includes, Q1. Construct a long short-term memory network, as Figure 6 shown. For each rower, divide the grip force historical data into a training set and a validation set according to a ratio, and sequentially input the training set into each node unit of the network constructed in chronological order. The output end outputs the paddle frequency of the current unit, and compares it with the true value to obtain the corresponding loss function. Each node unit corresponds to 4 (two cycles) rowing actions, and the first node unit also inputs an initial signal at the transmission layer; It is easy to understand that the signal strength is a function of time. By finding the inverse function, the reciprocal of the time interval corresponding to the adjacent maximum signal strength values can be obtained to calculate the paddle frequency. Since the physical strength of a paddler has a certain pattern within a period, the maximum signal strength values fluctuate after different numbers of paddles. By finding the pattern, the characteristic strength can be obtained, and thus the corresponding paddle frequency can also be predicted. Based on these two principles, through training with a large number of training sets, the current paddle frequency can be predicted from adjacent maximum signals.

[0029] Q2 uses the validation set to verify the accuracy rate and optimizes the network parameters using the loss function. Continuously alternate between such training and verification until the loss function is minimized and the accuracy rate stabilizes to complete the training. Q3 obtains the yaw degree data at the current moment and inputs all the grip force detection data of the paddlers at the current moment into the node units of the network that has completed training corresponding to the paddler, and outputs the predicted paddle frequency. , is the paddler number. When , here it is determined that , then for the paddlers rowing to the left in the forward direction, the predicted paddle frequency paddlers, is the actual paddle frequency of the paddler numbered at the current moment. The background server sends a prompt message to their sound-insulating earphones to pay attention to appropriately increasing the paddle frequency. For paddlers, a prompt message to pay attention to appropriately reducing the paddle frequency is sent, and for no prompt message is sent; when , then similarly, for the paddlers rowing to the right in the forward direction, corresponding prompt messages to reduce or increase the paddle frequency are sent, or no prompt message is sent. Q4 After another 5 seconds, new yaw degree data is obtained again. If , then a prediction result of force balance is given. Otherwise, continue to execute Q3 - Q4 until is satisfied.

[0030] Moreover, once is satisfied, a prompt message to maintain the paddle frequency is immediately sent to the sound-insulating earphones of the paddlers who are prompted. If the condition of still cannot be met after two consecutive executions of Q3, then the volume of the chant is controlled to increase to coordinate the paddle frequencies of all paddlers.

[0031] Embodiment 3 This embodiment will describe the method for testing the paddle frequency and force balance using the test device of Embodiment 1 that adopts the algorithm and model of Embodiment 2, specifically including the following steps: P1 According to as Figure 4The water area size shown, and multiple channels are set up, and camera devices are set on both banks at both ends of each channel. Each dragon boat is returned to the starting position, and the background server obtains the position information of the Beidou satellite positioning module on each dragon head. P2 All paddlers wear sound-insulating earphones (as Figure 1 shown), and upon hearing Figure 4 the starting command sent by the onshore PC computer shown as the background server, each dragon boat starts to move forward. The background server immediately obtains the position information of the Beidou satellite positioning module, the captured images of the camera devices on the corresponding channel banks, and the grip force detection data corresponding to all paddlers, so as to calculate the stroke rate based on the grip force detection data. P3 Calculate the yaw degree of the hull based on the captured images, and predict the force balance result through the grip force detection data of each paddler and the calculation result of the yaw degree, and send a prompt message to the sound-insulating earphones worn by the paddlers accordingly.

[0032] Thus, according to the method of the present invention, paddlers can obtain a real experience consistent with the on-site conditions during training and competitions, thereby creating more real training conditions for the competitions and quickly adapting, laying a foundation for achieving good results in the competitions.

Claims

1. The dragon boat paddle frequency and force balance test device under the use scenario is characterized by: It includes a grip detection device that is consistent with the number of dragon boat paddles, which is used to monitor the pressure generated by the fingers holding the paddle surface over time, so as to calculate the paddle frequency of each paddler, a camera device set at both ends of the track, and a marker set at the head and tail of the dragon boat, which is used to calculate the yaw degree of the boat body according to the video or multiple images taken by the camera device, and to build a model to predict the force balance result through the grip history data of each paddler and the calculation result of the yaw degree, as well as a soundproof headset worn by the paddler, a satellite positioning module set on the dragon head, and a background server on the shore of the water area, wherein, The grip detection device, camera device, soundproofing headset, and satellite positioning module all communicate with the background server, upload and save the change function, video or multiple images in the background server, perform the calculation and build a model to predict the force balance result in the background server, and send prompt information to the soundproofing headset worn by the rower.

2. The testing device according to claim 1, characterized in that: The paddle shaft of the rowing boat has a grip force detection part for installing a grip force detection device, and the grip force detection device includes a flexible substrate, one side of which is provided with a pressure sensor sheet, and the other side is provided with a collection amplifier electrically connected to the pressure sensor sheet, which is used to collect and amplify the pressure signal of the grip force, and send it to the backend server through the antenna hole of the paddle shaft where the antenna is set through the wireless transmission module electrically connected thereto; the method for calculating the paddling frequency of each rower is to find the time interval between two adjacent peaks on the variation function , then the propeller frequency .

3. The testing device according to claim 1, characterized in that: All of the soundproof headsets can be controlled by a background server to play the chant synchronously to coordinate the paddling rhythm of all rowers.

4. The testing device according to claim 2 or 3, characterized in that: The method for calculating the yaw degree includes: S1, the backend server receives the position of the dragon head sent by the satellite positioning module in real time, and obtains the real-time distance between it and the dragon head according to the position of the camera device set in front of the dragon head outside the water area , and according to the distance between it and the camera device set up behind the dragon's tail outside the water area , and the distance between the dragon head and dragon tail markers , calculate the distance between the marker set at the dragon's tail and the camera device set behind the dragon's tail outside the water area as ; S2 obtains the current video frame or the captured image, and respectively detects the distance between the camera and the camera head of the dragon and the rear of the dragon's tail. and And the horizontal distance of the crosshair in the field of view from the markers set at the dragon's head and tail and , calculate the horizontal distance of the dragon head and tail from the standard direction and , where the direction of the crosshairs projected on the connecting line of the sensing surfaces of the photographic devices and moving toward the boat is defined as the standard direction; S3 Yaw degree .

5. The testing device according to claim 4, characterized in that: ,but .

6. The testing device according to claim 5, characterized in that: The method of constructing a model to predict force balance results by using the grip force history data of each rower and the calculation results of the yaw degree includes: Q1 builds a long short-term memory network. For each rower, the grip force history data is divided into a training set and a validation set in proportion. The training set is used to input each node unit of the network constructed in chronological order in sequence. The output end outputs the paddling frequency of the current unit and compares it with the true value to obtain the corresponding loss function. Each node unit corresponds to at least one paddling action. The first node unit also inputs the initial signal in the transmission layer. Q2 uses the validation set to verify the accuracy and uses the loss function to optimize the network parameters. The training and verification are repeated alternately until the loss function is minimized, the accuracy is stable, and the training is completed. Q3 obtains the yaw degree data at the current moment, inputs the grip strength detection data of all rowers at the current moment into the node unit of the training network corresponding to the rower, and outputs the predicted paddling frequency , Number the rowers when , , then for the person paddling forward to the left, the predicted paddling frequency is , For the number The paddler's current real paddling frequency is sent by the backend server to his / her soundproof headset, reminding him / her to increase the paddling frequency appropriately. If the user No prompt message will be sent; when , similarly, for the person paddling forward to the right, a corresponding prompt message of lowering or increasing the paddling frequency is given, or no prompt message is given; Q4 After the preset time, re-acquire the new yaw degree data. , then the predicted result of force balance is given, otherwise continue to execute Q3-Q4 until it meets .

7. The testing device according to claim 6, characterized in that: Once satisfied , then the paddler will be prompted to maintain the paddling frequency through the soundproof headset. If the paddler still cannot reach the required paddling frequency after two consecutive rounds of Q3, If the conditions are met, the volume of the horn is increased to coordinate the paddling frequency of all rowers.

8. The testing device according to claim 6 or 7, characterized in that: The preset time is 3-10s.

9. The testing device according to claim 8, characterized in that: The backend server includes at least one of a PC, a portable computer, and a tablet computer.

10. A method for testing dragon boat paddle frequency and force balance in a usage scenario, characterized in that: The method adopts the testing device as described in any one of claims 1 to 9, and specifically comprises the following steps: P1 sets multiple waterways according to the size of the water area, and sets up cameras on both ends of each waterway to return each dragon boat to its starting position. The backend server obtains the position information of the satellite positioning module on each dragon head; P2 All rowers wear soundproof headsets and hear the start command sent by the background server. Each dragon boat starts to move forward. The background server immediately obtains the location information of the satellite positioning module, the captured video frames and images of the camera device on the shore of the corresponding channel, and the grip strength detection data of all rowers, so as to calculate the paddling frequency according to the grip strength detection data; P3 calculates the yaw degree of the boat based on the collected video frames and images, and predicts the force balance result through the grip strength detection data of each rower and the calculation result of the yaw degree, and sends prompt information to the noise-isolating headset worn by the rower accordingly.

Images