Intelligent path avoiding method and system for new energy vehicle on fire
By preprocessing and identifying the environmental data of new energy vehicles when they catch fire, generating and optimizing driving paths, the problem of inaccurate planning of new energy vehicles' evasion paths is solved, and the effect of automatically avoiding pedestrians and reducing property losses is achieved.
Patent Information
- Application Number
- CN202411932996.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-26
- Publication Date
- 2025-04-15
AI Technical Summary
When a new energy vehicle catches fire, the avoidance path planning is inaccurate, resulting in injury and losses to pedestrians and public property.
By collecting and preprocessing the environmental data of new energy vehicles that have caught fire, including license plate color data and temperature perception data, using near-infrared depth cameras and infrared cameras to identify the fire range, perform adaptive fire denoising processing, generate initial driving paths and optimize them into predictive driving paths, and finally formulate driving strategies and generate operation instructions to control vehicle evasion.
It has achieved that new energy vehicles can automatically plan their paths when they catch fire, avoid pedestrians in a timely manner, reduce the loss of public property, and improve path reliability and selection accuracy.
Smart Images
Figure CN119831120A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of new energy, and in particular to a method and system for intelligently avoiding a path for a new energy vehicle that is on fire. Background Art
[0002] With the popularization of new energy vehicles, the intelligence of new energy vehicles has been improved. All parts in them are driven by electricity, which reduces the technical difficulty of coordination between various parts and effectively improves the safety of automatic control. And for new energy vehicles, upgrading to intelligence and networking is a trend in future development.
[0003] However, there are more and more new energy vehicles catching fire when they are involved in traffic accidents. The fire is caused by the heat of the battery, and the fire spreads quickly. The rapid fire causes casualties of varying degrees. With the increasing number of motor vehicles and the frequent occurrence of traffic accidents, the safety and reliability requirements for new energy vehicles are also getting higher and higher. Therefore, the problem of how to plan an avoidance path after a new energy vehicle collision needs to be solved urgently. Summary of the invention
[0004] The present invention provides an intelligent avoidance path method and system for a new energy vehicle on fire, so as to solve the technical problem that the avoidance path planning is inaccurate when a new energy vehicle on fire catches fire, causing harm and loss to pedestrians and public property. The method can enable the new energy vehicle to automatically plan a path when a fire occurs, avoid pedestrians in time, and reduce the loss of public property.
[0005] Embodiment 1:
[0006] A method for intelligently avoiding a fire-prone new energy vehicle, comprising the following steps:
[0007] S1. Collect and pre-process the environmental data of the new energy vehicle on fire, the environmental data of the new energy vehicle on fire includes the license plate color data, use the near-infrared depth camera to obtain the license plate image of the car, and obtain the vertical height of each pixel point and the near-infrared depth camera and the RGB data of each pixel point according to the license plate of the car;
[0008] S2. The environmental data of the new energy vehicle on fire also includes temperature sensing data, using an infrared camera to identify the boundary contour line of the car on fire, obtain the boundary contour area, and generate a fire range image;
[0009] S3. Set a threshold value, and binarize the car license plate image according to the threshold condition to obtain a binary image;
[0010] S4. Perform adaptive fire denoising to obtain the fire range data after noise filtering, and transmit it to the alarm and warning processing in time;
[0011] S5. Generate a preliminary driving path of the new energy vehicle on fire based on the vehicle temperature and fire intensity, optimize the preliminary driving path based on the preliminary driving path and environmental information data after intelligent processing, obtain a predictive driving path, formulate a driving strategy based on the predictive driving path, and generate operating instructions; convert the operating instructions into vehicle control instructions to control the actual actions of the vehicle.
[0012] Preferably, S4 specifically includes:
[0013] A preliminary denoising and filtering preprocessing algorithm is used to implement multi-level time-frequency domain analysis of the fire range data for preprocessing.
[0014] Preferably, the method further specifically includes: introducing an improved non-local mean algorithm to perform preliminary denoising filtering on the temperature sensing data.
[0015] As a preferred embodiment, S2 specifically includes: using a fusion algorithm based on multi-dimensional weight optimization to perform data fusion processing on the pre-processed temperature sensing data. The fusion algorithm based on multi-dimensional weight optimization introduces a multi-dimensional weight optimization mechanism to dynamically adjust the weights of different sensor data, monitor the temperature of new energy vehicles, and also monitor the license plate color of new energy vehicles.
[0016] As a preferred embodiment, it also specifically includes: enhancing the temperature perception data after noise filtering through a data enhancement algorithm based on a multi-level recursive convolutional network; predicting and correcting the temperature perception data after noise filtering by combining a multi-level recursive convolution with a time series neural network.
[0017] Preferably, S5 specifically includes: presetting a first limit value of the driving path behavior cardinality to be LX1, and a second limit value of the driving path behavior cardinality to be LX2, wherein LX1<LX2;
[0018] The driving path behavior cardinality LX is compared with the first limit value LX1 of the driving path behavior cardinality and the second limit value LX2 of the driving path behavior cardinality:
[0019] If LX<LX1, the driving paths within this range are recorded as the first selected path group;
[0020] If LX1≤LX<LX2, the driving paths within this range are recorded as the second selection group of paths;
[0021] If LX ≥ LX2, the driving paths within this range are recorded as the third selection group of paths.
[0022] As a preferred method, it also includes: arranging all the candidate paths in the same path group in ascending order of resolution value, recording the candidate path corresponding to the smallest resolution value as the driving path of the new energy vehicle that caught fire, and completing the selection of the optimal path for the new energy vehicle that caught fire.
[0023] Preferably, the method includes: according to the optimal path, the new energy vehicle on fire automatically goes to a road section with fewer vehicles and fewer people, and reports the location information of the new energy vehicle on fire to the police.
[0024] A fire-prone new energy vehicle intelligent avoidance path system, using the above-mentioned fire-prone new energy vehicle intelligent avoidance path method, including
[0025] The first acquisition module collects and pre-processes the environmental data of the new energy vehicle on fire, wherein the environmental data of the new energy vehicle on fire includes the color data of the license plate, obtains the image of the license plate of the vehicle by using a near-infrared depth camera, and obtains the vertical height of each pixel point and the near-infrared depth camera and the RGB data of each pixel point according to the license plate of the vehicle;
[0026] The second acquisition module, the environmental data of the new energy vehicle on fire also includes temperature perception data, uses an infrared camera to identify the fire boundary contour line of the vehicle, obtains the boundary contour area, and generates a fire range image;
[0027] The processing module sets a threshold value, performs binarization processing on the automobile license plate image according to the threshold condition, and obtains a binary image;
[0028] The denoising module performs adaptive fire denoising to obtain the fire range data after noise filtration, and transmits it to the alarm and warning processing in time;
[0029] The calculation module generates a preliminary driving path of the new energy vehicle on fire according to the vehicle temperature and the fire intensity, optimizes the preliminary driving path based on the preliminary driving path and the environmental information data after intelligent processing, obtains a predictive driving path, formulates a driving strategy based on the predictive driving path, generates operation instructions, and converts the operation instructions into vehicle control instructions to control the actual actions of the vehicle.
[0030] The beneficial effects of the technical solution of the present invention are:
[0031] 1. The calculation formula of the optimal path reliability is:
[0032]
[0033] Among them, E j represents the data collection efficiency of the jth path; R j represents the reliability of the jth path; z j represents the number of detection devices in the jth path; D jsrepresents the data volume of the sth passerby in the jth path; f js represents the walking sampling frequency of the sth pedestrian in the jth path; l js represents the distance between the sth pedestrian and the burning vehicle in the jth path; l max It indicates the maximum distance between pedestrians and the vehicle on fire; σ indicates the standard deviation of the number of people. It effectively improves the reliability of the route and reduces human and financial losses.
[0034] At the same time, the burning car will make an intelligent prediction of its driving trajectory during the driving process. During the path optimization process, the result of the node cost function will be used as input, which will directly affect the objective function of the intelligent multi-layer path optimization algorithm and integrate multiple levels of environmental adaptability.
[0035] After selecting the optimal path, each sub-area is optimized hierarchically to adjust the path selection and traffic distribution in each sub-area. The global coordination mechanism integrates the hierarchical optimization results of each sub-area by using the global optimization objective function to obtain the optimal traffic distribution and path selection in the network. The formula of the global optimization objective function is:
[0036]
[0037] in, is the global optimization objective function; R is the number of sub-regions; ω r (t+1) is the weight of the rth sub-region at time t+1; P r is the path selection result of the rth sub-region; φ(t+1) is the weight of the global adjustment factor at time t+1; M is the number of global adjustment factors; is the network performance indicator related to the qth global adjustment factor; P q It is the path selection result related to the qth global adjustment factor. It improves the accuracy of path selection and reduces personal injury and economic losses. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 This is a flow chart of the intelligent avoidance path method of the present invention. DETAILED DESCRIPTION
[0039] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0040] Embodiment 1:
[0041] A method for intelligently avoiding the path of a new energy vehicle on fire, such as Figure 1 As shown, the following steps are included:
[0042] S1. Collect and pre-process the environmental data of the new energy vehicle on fire, the environmental data of the new energy vehicle on fire includes the license plate color data, use the near-infrared depth camera to obtain the license plate image of the car, and obtain the vertical height of each pixel point and the near-infrared depth camera and the RGB data of each pixel point according to the license plate of the car;
[0043] Specifically, the near-infrared depth camera is used to illuminate and identify the car license plate image, and the original data group (X, Y, Z, G) is output; wherein X represents the horizontal coordinate point of the car license plate image pixel, Y represents the vertical coordinate point of the car license plate image pixel, Z represents the vertical height between the car license plate image pixel and the near-infrared depth camera, and G represents the intensity value of the car license plate image pixel in the green channel.
[0044] For each pixel, compare the intensity values of the three channels R, G, and B to find the maximum and minimum values, which are used to calculate the brightness V and saturation S.
[0045] The brightness V of the pixel is determined based on the maximum RGB data; the brightness (V) in the HSV color space is determined by the maximum value of the RGB value. For this, the brightness V formula is: Where N i is the number of pixels.
[0046] S2. The environmental data of the new energy vehicle on fire also includes temperature sensing data, using an infrared camera to identify the boundary contour line of the car on fire, obtain the boundary contour area, and generate a fire range image;
[0047] S2, specifically includes:
[0048] The pre-processed temperature sensing data is fused using a fusion algorithm based on multi-dimensional weight optimization. The fusion algorithm based on multi-dimensional weight optimization introduces a multi-dimensional weight optimization mechanism to dynamically adjust the weights of different sensor data, monitor the temperature of new energy vehicles, and also monitor the license plate color of new energy vehicles.
[0049] It also specifically includes:
[0050] An improved non-local means algorithm is introduced to perform preliminary denoising filtering on the temperature sensing data.
[0051] Use the improved non-local means algorithm for processing. The specific steps are as follows:
[0052] The non-local mean algorithm is used for preliminary denoising filtering, and the calculation formula is as follows:
[0053]
[0054] in, is the subband signal of the sth level after preliminary denoising filtering at time t and frequency f of sensor i; h is is the similarity parameter; k is the neighborhood index in the non-local means algorithm, indicating the kth neighborhood point in the search window; Ω is is the search window, which represents the neighborhood range in the non-local means algorithm; x is (t+k,f) represents the subband signal of the sth level after preliminary denoising filtering of sensor i at time t+k and frequency f.
[0055] It also specifically includes:
[0056] The temperature sensing data after noise filtering is enhanced by a data enhancement algorithm based on a multi-level recursive convolutional network; the temperature sensing data after noise filtering is predicted and corrected by combining multi-level recursive convolution with a temporal neural network.
[0057] The environmental data after noise filtering is stabilized using a data enhancement algorithm based on a multi-level recursive convolutional network. The data enhancement algorithm combines multi-level recursive convolution with a temporal neural network to perform multi-level prediction and correction on the environmental data after noise filtering to ensure the stability of the data in dynamic scenes. The specific implementation process is as follows:
[0058] Perform multi-level recursive convolution processing on the noise-filtered environmental data to extract spatiotemporal features. The calculation formula is as follows:
[0059]
[0060] in, is the spatiotemporal convolution feature of the lth convolutional layer at time t, is the activation function, which is selected based on expert experience. is the convolution kernel, x' f (t,f) is the environmental data after noise filtering, is the bias term of the lth convolutional layer at time t, is the feature weight coefficient of the lth convolutional layer at time t to the mth convolutional layer at time t-1, is the number of convolutional layers, is the spatiotemporal convolution feature of the mth convolutional layer at time t-1.
[0061] S3. Set a threshold, and binarize the car license plate image according to the threshold condition to obtain a binary image; binarize the car license plate to form a binary black and white image, reduce the influence of other colors on the recognition of green, and ensure that the brightness and saturation of the license plate are greater than 60% of the overall range of the license plate. The vehicle can be identified as a new energy vehicle, reducing the influence of license plate obstructions on license plate recognition and improving recognition accuracy.
[0062] S4. Perform adaptive fire denoising to obtain the fire range data after noise filtering, and transmit it to the alarm and warning processing in time;
[0063] S4 specifically includes:
[0064] A preliminary denoising and filtering preprocessing algorithm is used to implement multi-level time-frequency domain analysis of the fire range data for preprocessing.
[0065] S5. Generate a preliminary driving path of the new energy vehicle on fire based on the vehicle temperature and fire intensity, optimize the preliminary driving path based on the preliminary driving path and environmental information data after intelligent processing, obtain a predictive driving path, formulate a driving strategy based on the predictive driving path, and generate operating instructions; convert the operating instructions into vehicle control instructions to control the actual actions of the vehicle.
[0066] S5 specifically includes: presetting a first limit value of the driving path behavior cardinality as LX1, and a second limit value of the driving path behavior cardinality as LX2, wherein LX1<LX2;
[0067] The driving path behavior cardinality LX is compared with the first limit value LX1 of the driving path behavior cardinality and the second limit value LX2 of the driving path behavior cardinality:
[0068] If LX<LX1, the driving paths within this range are recorded as the first selected path group;
[0069] If LX1≤LX<LX2, the driving paths within this range are recorded as the second selection group of paths;
[0070] If LX ≥ LX2, the driving paths within this range are recorded as the third selection group of paths.
[0071] The method also includes: arranging all candidate paths in the same path group in ascending order of analytical value, recording the candidate path corresponding to the smallest analytical value as the driving path of the new energy vehicle on fire, and completing the selection of the optimal path for the new energy vehicle on fire.
[0072] Including: according to the optimal path, the new energy vehicle that caught fire automatically goes to a road section with fewer vehicles and fewer people, and reports the location information of the new energy vehicle that caught fire to the police.
[0073] The calculation formula of the optimal path reliability is:
[0074]
[0075] Among them, E j represents the data collection efficiency of the jth path; R j represents the reliability of the jth path; z j represents the number of detection devices in the jth path; D js represents the data volume of the sth passerby in the jth path; f js represents the walking sampling frequency of the sth pedestrian in the jth path; l js represents the distance between the sth pedestrian and the burning vehicle in the jth path; l max It indicates the maximum distance between pedestrians and the vehicle on fire; σ indicates the standard deviation of the number of people. It effectively improves the reliability of the route and reduces human and financial losses.
[0076] At the same time, the burning car will make an intelligent prediction of its driving trajectory during the driving process. During the path optimization process, the result of the node cost function will be used as input, which will directly affect the objective function of the intelligent multi-layer path optimization algorithm and integrate multiple levels of environmental adaptability.
[0077] After selecting the optimal path, each sub-area is optimized hierarchically to adjust the path selection and traffic distribution in each sub-area. The global coordination mechanism integrates the hierarchical optimization results of each sub-area by using the global optimization objective function to obtain the optimal traffic distribution and path selection in the network. The formula of the global optimization objective function is:
[0078]
[0079] in, is the global optimization objective function; R is the number of sub-regions; ω r (t+1) is the weight of the rth sub-region at time t+1; P r is the path selection result of the rth sub-region; φ(t+1) is the weight of the global adjustment factor at time t+1; M is the number of global adjustment factors; is the network performance indicator related to the qth global adjustment factor; P q It is the path selection result related to the qth global adjustment factor. It improves the accuracy of path selection and reduces personal injury and economic losses.
[0080] Embodiment 2:
[0081] A fire-prone new energy vehicle intelligent avoidance path system, using the above-mentioned fire-prone new energy vehicle intelligent avoidance path method, including
[0082] The first acquisition module collects and pre-processes the environmental data of the new energy vehicle on fire, wherein the environmental data of the new energy vehicle on fire includes the color data of the license plate, obtains the image of the license plate of the vehicle by using a near-infrared depth camera, and obtains the vertical height of each pixel point and the near-infrared depth camera and the RGB data of each pixel point according to the license plate of the vehicle;
[0083] The second acquisition module, the environmental data of the new energy vehicle on fire also includes temperature perception data, uses an infrared camera to identify the fire boundary contour line of the vehicle, obtains the boundary contour area, and generates a fire range image;
[0084] The processing module sets a threshold value, performs binarization processing on the automobile license plate image according to the threshold condition, and obtains a binary image;
[0085] The denoising module performs adaptive fire denoising to obtain the fire range data after noise filtration, and transmits it to the alarm and warning processing in time;
[0086] The calculation module generates a preliminary driving path of the new energy vehicle on fire according to the vehicle temperature and the fire intensity, optimizes the preliminary driving path based on the preliminary driving path and the environmental information data after intelligent processing, obtains a predictive driving path, formulates a driving strategy based on the predictive driving path, generates operation instructions, and converts the operation instructions into vehicle control instructions to control the actual actions of the vehicle.
[0087] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0088] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0089] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.
Claims
1. A method for intelligently avoiding the path of a new energy vehicle on fire, characterized in that: The following steps are involved: S1. Collect and pre-process the environmental data of the new energy vehicle on fire, the environmental data of the new energy vehicle on fire includes the license plate color data, use the near-infrared depth camera to obtain the license plate image of the car, and obtain the vertical height of each pixel point and the near-infrared depth camera and the RGB data of each pixel point according to the license plate of the car; S2. The environmental data of the new energy vehicle on fire also includes temperature sensing data, using an infrared camera to identify the boundary contour line of the car on fire, obtain the boundary contour area, and generate a fire range image; S3. Set a threshold value, and binarize the car license plate image according to the threshold condition to obtain a binary image; S4. Perform adaptive fire denoising to obtain the fire range data after noise filtering, and transmit it to the alarm and warning processing in time; S5. Generate a preliminary driving path of the new energy vehicle on fire according to the vehicle temperature and the fire intensity, optimize the preliminary driving path based on the preliminary driving path and the environmental information data after intelligent processing, obtain a predictive driving path, formulate a driving strategy based on the predictive driving path, and generate an operation instruction; Convert operating instructions into vehicle control instructions to control the actual actions of the vehicle.
2. A method for intelligently avoiding a fire-caused new energy vehicle according to claim 1, characterized in that: S4 specifically includes: A preliminary denoising and filtering preprocessing algorithm is used to implement multi-level time-frequency domain analysis of the fire range data for preprocessing.
3. A method for intelligently avoiding a fire-caused new energy vehicle according to claim 2, characterized in that: It also specifically includes: An improved non-local means algorithm is introduced to perform preliminary denoising filtering on the temperature sensing data.
4. A method for intelligently avoiding a fire-caused new energy vehicle according to claim 3, characterized in that: S2, specifically includes: The pre-processed temperature sensing data is fused using a fusion algorithm based on multi-dimensional weight optimization. The fusion algorithm based on multi-dimensional weight optimization introduces a multi-dimensional weight optimization mechanism to dynamically adjust the weights of different sensor data, monitor the temperature of new energy vehicles, and also monitor the license plate color of new energy vehicles.
5. A method for intelligently avoiding a fire-caused new energy vehicle according to claim 3, characterized in that: It also specifically includes: The temperature sensing data after noise filtering is enhanced by a data enhancement algorithm based on a multi-level recursive convolutional network; the temperature sensing data after noise filtering is predicted and corrected by combining multi-level recursive convolution with a temporal neural network.
6. A method for intelligently avoiding a fire-caused new energy vehicle according to claim 1, characterized in that: S5 specifically includes: presetting a first limit value of the driving path behavior cardinality as LX1, and a second limit value of the driving path behavior cardinality as LX2, wherein LX1<LX2; The driving path behavior cardinality LX is compared with the first limit value LX1 of the driving path behavior cardinality and the second limit value LX2 of the driving path behavior cardinality: If LX<LX1, the driving paths within this range are recorded as the first selected path group; If LX1≤LX<LX2, the driving paths within this range are recorded as the second selection group of paths; If LX ≥ LX2, the driving paths within this range are recorded as the third selection group of paths.
7. A method for intelligently avoiding a fire-caused new energy vehicle according to claim 6, characterized in that: Also includes: All candidate paths in the same path group are arranged in ascending order of analytical value, and the candidate path corresponding to the smallest analytical value is recorded as the driving path of the new energy vehicle on fire, thereby completing the selection of the optimal path for the new energy vehicle on fire.
8. An intelligent avoidance path system for new energy vehicles on fire according to claim 7, characterized in that: include: According to the optimal route, the new energy vehicle that caught fire automatically goes to a road section with fewer vehicles and people, and reports the location information of the new energy vehicle that caught fire to the police.
9. An intelligent avoidance path system for new energy vehicles on fire, using an intelligent avoidance path method for new energy vehicles on fire as claimed in any one of claims 1 to 8, characterized in that: include: The first acquisition module is used to collect and pre-process the environmental data of the new energy vehicle on fire, wherein the environmental data of the new energy vehicle on fire includes the color data of the license plate, and obtain the image of the license plate of the vehicle by using a near-infrared depth camera, and obtain the vertical height of each pixel point and the near-infrared depth camera and the RGB data of each pixel point according to the license plate of the vehicle; The second acquisition module is used to collect environmental data of the new energy vehicle on fire, including temperature sensing data, and use an infrared camera to identify the boundary contour line of the car on fire, obtain the boundary contour area, and generate a fire range image; The processing module sets a threshold value and is used to perform binarization processing on the automobile license plate image according to the threshold condition to obtain a binary image; De-noising module is used to perform adaptive fire denoising processing to obtain the fire range data after noise filtering, and transmit it in time for alarm and warning processing; A calculation module is used to generate a preliminary driving path of the new energy vehicle on fire according to the vehicle temperature and the fire intensity, optimize the preliminary driving path based on the preliminary driving path and the environmental information data after intelligent processing, obtain a predictive driving path, formulate a driving strategy based on the predictive driving path, and generate an operation instruction; Convert operating instructions into vehicle control instructions to control the actual actions of the vehicle.