Evaluation method and device for urban night light environment quality

Abstract

The invention provides an evaluation method and device for urban night light environment quality, and relates to the technical field of urban night space quality evaluation.The device comprises a data acquisition sub-device and a terminal, the data acquisition sub-device is used for acquiring multi-modal data, and the terminal is used for receiving the multi-modal data; the multi-modal data comprises human body physiological data, night environment data and human body position data, and the terminal is used for generating a night light environment-emotion quality evaluation map according to the multi-modal data, determining an area type on the night light environment-emotion quality evaluation map according to an emotion state value, and urban night light environment quality evaluation is carried out on different types of regions, so that accurate and reliable quantitative data can be provided, and urban night space light environment quality evaluation is more objective and accurate.

Description

Technical Field

[0001] The present application relates to the technical field of urban night space quality assessment, and in particular to a method and device for evaluating the quality of urban night light environment. Background Art

[0002] The evaluation of urban night space quality has always been a core research issue in the fields of landscape architecture, urban planning and environmental psychology. Traditional evaluation methods mostly use subjective evaluation methods, such as questionnaires, interviews and focus groups, which rely on self-reports from participants. However, subjective feelings are often obscure and difficult to describe accurately, and are affected by individual differences and situational factors. The data consistency and repeatability are poor, making it difficult to quantify and compare. Therefore, these evaluation methods are highly subjective and unstable, and it is difficult to provide accurate and reliable quantitative data, which makes these evaluation methods have obvious limitations when applied on a large scale and cannot effectively meet the current research needs for high-precision and objective evaluation methods. Summary of the invention

[0003] The purpose of this application is to provide an evaluation device for the quality of urban nighttime light environment, which can provide accurate and reliable quantitative data, making the evaluation of the quality of urban nighttime light environment more objective and accurate.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a device for evaluating the quality of urban nighttime light environment, comprising:

[0006] Data collection sub-devices and terminals;

[0007] The data acquisition sub-device is communicatively connected with the terminal;

[0008] The data acquisition sub-device is used to collect multi-modal data, wherein the multi-modal data includes human physiological data, nighttime environmental data and human position data;

[0009] The terminal is used to generate a night light environment-emotional quality evaluation map according to the multimodal data, determine the area type on the night light environment-emotional quality evaluation map according to the emotional state value, and evaluate the urban night light environment quality for different types of areas, wherein the emotional state value is a variable value calculated based on the multimodal data, and the area type includes an abnormal area and a non-abnormal area.

[0010] In a second aspect, the present application provides a method for evaluating the quality of urban nighttime light environment, comprising:

[0011] Acquiring multimodal data, wherein the multimodal data includes human physiological data, nighttime environmental data, and human position data;

[0012] generating a nighttime light environment-emotional quality evaluation map according to the multimodal data;

[0013] Determining the area type on the night light environment-emotional quality evaluation map according to the emotional state value, wherein the emotional state value is a variable value calculated according to the multimodal data, and the area type includes an abnormal area and a non-abnormal area;

[0014] Evaluate the quality of urban night light environment for different types of areas.

[0015] The present application provides a method and device for evaluating the quality of urban nighttime light environment. The device includes a data acquisition sub-device and a terminal. The data acquisition sub-device is used to collect multimodal data, and the multimodal data includes human physiological data, nighttime environment data and human position data. The terminal is used to generate a nighttime light environment-emotional quality evaluation map according to the multimodal data, determine the area type on the nighttime light environment-emotional quality evaluation map according to the emotional state value, and evaluate the quality of the urban nighttime light environment for different types of areas. Through the collection and processing of multimodal data, it is possible to quantify individual emotional states and light environment parameters in real time, more objectively and accurately evaluate the impact of the urban nighttime light environment on individual emotional states, and provide a basis for the optimal design of the urban light environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is a schematic diagram of the structure of a device for evaluating the quality of urban nighttime light environment in Example 1 of the present application;

[0018] Figure 2 This is a schematic diagram of the structure of the data acquisition sub-device in Example 1 of the present application;

[0019] Figure 3 This is a schematic diagram of the partial structure of the data acquisition sub-device in Example 1 of the present application;

[0020] Figure 4 This is a flow chart of a method for evaluating the quality of urban nighttime light environment in Example 2 of the present application.

[0021] Reference numerals:

[0022] 1-first camera; 2-skin electronic unit; 3-core electronic unit; 4-noise sensor; 5-GPS subunit; 6-photometric data measurement sensor; 7-second camera; 8-temperature sensor; 9-humidity sensor; 10-wind speed sensor; 11-data preprocessing module; 12-data storage module; 13-communication transmission module; 14-power module. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0025] Example 1

[0026] like Figure 1 As shown, this embodiment provides a device for evaluating the quality of urban nighttime light environment, including:

[0027] Data collection sub-devices and terminals.

[0028] The data acquisition sub-device is communicatively connected to the terminal.

[0029] The data acquisition sub-device shown is used to collect multimodal data, wherein the multimodal data includes human physiological data, nighttime environmental data and human position data, the human physiological data includes human facial expression images, skin conductance data, and electrocardiogram data; the nighttime environmental data includes photometric data, city image data, ambient temperature, ambient humidity, wind speed and noise, and the photometric data includes spectral data and stroboscopic data.

[0030] The terminal is used to generate a night light environment-emotional quality evaluation map according to the multimodal data, determine the area type on the night light environment-emotional quality evaluation map according to the emotional state value, and evaluate the urban night light environment quality for different types of areas, wherein the emotional state value is a variable value calculated based on the multimodal data, and the area type includes an abnormal area and a non-abnormal area.

[0031] The terminal further comprises:

[0032] The human physiological data processing module is used to extract characteristic values ​​according to the human physiological data, take the characteristic values ​​as input, and calculate the emotional state value using the emotion calculation model, wherein the emotional state value includes emotional valence and emotional arousal.

[0033] The data integration module is used to establish an association relationship between the emotional state value, the nighttime environment data and the human body position data by taking the timestamp and the spatial coordinates as indexes.

[0034] The emotional state value processing module is used to determine whether the emotional state value is abnormal based on covariates, eliminate abnormal emotional state values, and use an interpolation algorithm to interpolate the eliminated emotional state values ​​to obtain processed emotional state values, wherein the ambient temperature, ambient humidity, wind speed and noise in the nighttime environmental data are used as the covariates.

[0035] The night light environment-emotional quality evaluation map generation module is used to generate a night light environment-emotional quality evaluation map according to the processed emotional state value, the human body position data, and the photometric data and city image data in the night environment data.

[0036] The area type classification module is used to perform spatial statistical analysis on the processed emotional state values ​​on the night light environment-emotional quality evaluation map, and determine the area type on the night light environment-emotional quality evaluation map according to the analysis results.

[0037] The evaluation module is used to evaluate the quality of urban night light environment for different types of areas.

[0038] Light stimulation affects people's emotions directly or indirectly through visual channels and non-visual channels. The visual channel mainly involves the stimulation of light on retinal cones and rods, affecting people's visual function, mental workload and other related cognitive activities; while the non-visual channel transmits information to the suprachiasmatic nucleus (SCN) in the brain through ipRGCs (intrinsically photosensitive retinalganglion cells, retinal ganglion cells of the medial geniculate nucleus), affecting people's circadian rhythm and thus affecting their emotional state. Studies have shown that specific lighting conditions (such as cool temperature and high-intensity blue light stimulation) can significantly improve an individual's attention and alertness, or induce certain physiological reactions (such as increased heart rate, increased skin electrical activity, etc.).

[0039] This embodiment can quantitatively analyze the changes in the emotional state of individuals in different scenarios by real-time detection of multimodal physiological signals (including but not limited to electrocardiogram, galvanic skin response, etc.) of pedestrians in the city's outdoor environment at night, and combined with emotion analysis technology. This method not only helps to understand the impact of the light environment on human psychological and physiological states, but also provides a quantifiable basis for optimizing the design of nighttime light environments.

[0040] Research has found that existing urban street environment data collection devices mainly rely on built-in sensors and detection technology to record the wearer's physiological state and environmental parameters. However, most devices are only designed for daytime street data collection and have significant deficiencies when used at night, specifically in the following aspects:

[0041] ① Limitations of single-modal information collection: Most devices only collect a single physiological indicator (such as heart rate or skin conductance), ignoring the integration of multimodal information. This single data collection method cannot fully reflect the multi-dimensional perceptual response in a complex environment.

[0042] ② Insufficient nighttime data collection function: Existing devices are mainly designed for daytime environments and lack collection functions for nighttime light environments, such as illumination, color temperature, and low-light high-definition video data. The accuracy and completeness of data collection in low-light environments are insufficient.

[0043] ③ Multimodal data has poor synchronization and anti-interference ability: Multimodal data is susceptible to external interference during collection, resulting in data asynchrony and affecting analysis accuracy. Problems such as signal transmission delay and sensor interference are common.

[0044] In this regard, this embodiment further designs a portable data collection device (i.e., a data collection sub-device) capable of integrating multi-modal physiological data and environmental data, such as Figure 2 and Figure 3 As shown, the data acquisition sub-device is a wearable helmet, and the data acquisition sub-device includes:

[0045] Shell, data acquisition module, data preprocessing module 11 and communication transmission module 13.

[0046] The data acquisition module, the data preprocessing module 11 and the communication transmission module 13 are all located on the housing.

[0047] The data preprocessing module 11 is connected to the data acquisition module and the communication transmission module 13 respectively.

[0048] The data acquisition module is used to acquire the multimodal data, wherein the multimodal data includes human physiological data, nighttime environment data and human position data.

[0049] The data acquisition module also includes: a human physiological data acquisition unit, a nighttime environment data acquisition unit and a position information acquisition unit.

[0050] The human physiological data acquisition unit, the nighttime environment data acquisition unit and the position information acquisition unit are all connected to the data preprocessing module 11 .

[0051] The human physiological data acquisition unit is used to acquire the human physiological data, wherein the human physiological data includes human facial expression images, skin conductance data and electrocardiogram data.

[0052] The human physiological data acquisition unit is composed of multiple sensor modules for measuring human vital characteristics, including: the first camera 1 (capturing facial expressions), the skin electronic unit 2 (collecting skin conductance data), and the heart electronic unit 3 (obtaining electrocardiogram signals). These sensor modules are responsible for collecting human physiological data and providing basic data for the analysis of the quality of urban night light environment.

[0053] Specifically:

[0054] Facial expression shooting subunit (i.e., the first camera 1): It is installed 15cm in front of the face through a bracket, which optimizes the viewing angle and distance of facial expression capture and ensures the collection of high-precision facial image data. It supports near-infrared and normal shooting modes, with a resolution of 1080p and a frame rate of 30fps and a viewing angle of 90 degrees, which is used to capture clear facial expression images; it has an automatic light compensation function, supports shooting in low-light environments at night, and is suitable for accurate capture in low-light environments.

[0055] Skin electronic unit 2: Installed on the right side of the helmet, the sensor contacts the belly of the finger and collects skin conductance data with an accuracy of ±0.1μS and a sampling frequency of 128Hz.

[0056] Cardiovascular electronic unit 3: It is placed on the left side of the forehead of the helmet. The sensor touches the earlobe and collects the ECG data at the earlobe in real time. The sampling frequency is 1024Hz.

[0057] The nighttime environment data acquisition unit is used to collect the nighttime environment data, wherein the nighttime environment data includes photometric data (spectral data and stroboscopic data), city image data, ambient temperature, ambient humidity, wind speed and noise.

[0058] The nighttime environmental data collection unit includes: a photometric data measurement sensor 6 (capturing spectral data and stroboscopic data at or near human eyes), a second camera 7 (recording environmental images, i.e., urban image data), a temperature sensor 8, a humidity sensor 9, a wind speed sensor 10, and a noise sensor 4. These sensors can cooperate with each other to synchronously measure multiple environmental parameters and provide complete environmental background information for data analysis.

[0059] Specifically:

[0060] Photometric data measurement sensor 6: Installed in the middle of the helmet forehead, it captures photometric data at the human eye / near human eye, can measure wavelengths from 380 to 780 nm, has a spectral resolution of 0.1 nm, illuminance from 0.1 lx to 20,000 lx, color temperature from 1000 K to 100000 K, and has a sensor size of 35×35 mm.

[0061] The second camera 7 is installed on the top of the head, with a 120-degree wide-angle view, a size of 35×35 mm, supports high-definition images and low-light shooting, captures urban image data from the perspective of pedestrians / near pedestrians, and is suitable for shooting in low-light environments.

[0062] Temperature / humidity sensor 9: installed at the front of the helmet, the ambient temperature measurement range is -40℃ to 85℃, the humidity range is 0-100%RH, and the sensor size is 10×20mm.

[0063] Wind speed sensor 10: installed on the front of the helmet, with a measurement range of 0.1m / s to 30m / s and an accuracy of ±0.1m / s.

[0064] Noise sensor 4: Installed on the front of the helmet, the measurement range is 30dBA to 130dBA, and the accuracy is ±1.5dB.

[0065] The position information acquisition unit is used to acquire the human body position data.

[0066] The location information acquisition unit is installed on the top of the helmet and consists of a GPS subunit 5, which has an accuracy of between 0.5 and 2 meters and supports high-frequency data updates (1Hz) to collect real-time location information and movement trajectories of personnel; in addition, it also integrates an inertial navigation system to enhance the accuracy of outdoor positioning, especially in unstable signal conditions. Through efficient connection with the power system, the unit ensures continuous positioning accuracy in various environmental conditions and works in conjunction with other systems to provide precise geographic location reference for data analysis.

[0067] The data preprocessing module 11 is used to preprocess the multimodal data.

[0068] The data preprocessing module 11 also includes an anomaly detection and correction unit and a data synchronization and fusion unit.

[0069] The abnormality detection and correction unit is connected to the data acquisition module and the data synchronization and fusion unit respectively.

[0070] The data synchronization and fusion unit is connected to the communication transmission module 13 .

[0071] The anomaly detection and correction unit is used to identify abnormal situations of the multimodal data, and perform anomaly correction and alarm, wherein the abnormal situations include signal loss, data noise and equipment failure. For example, through an abnormal recognition model (such as signal loss detection, noise screening), outliers in the data are automatically identified, and an interpolation algorithm or a correction method based on machine learning is used to correct the data to ensure data quality.

[0072] The data synchronization and fusion unit is used to process the corrected multimodal data using a time synchronization algorithm to obtain time-synchronized multimodal data. For example, based on a timestamp alignment algorithm, human physiological data (such as skin electricity, electrocardiogram) and nighttime environmental data are synchronized to ensure data consistency in the time dimension.

[0073] Time synchronization and data fusion technology are used to achieve millisecond-level synchronization and denoising of multimodal data to ensure data accuracy and consistency.

[0074] The communication transmission module 13 is used to transmit the pre-processed multimodal data to the terminal.

[0075] Users can visualize and interact with data through terminals (such as computers, tablets or mobile phones) to display data status and analysis results. The terminal also includes a physiological feedback processing module for the human body and an urban night space data construction module. The data output by the two modules is coupled and analyzed to provide support for the optimization design of the urban night light environment.

[0076] The communication transmission module 13 is used to transmit the pre-processed multimodal data to the terminal (such as a computer, tablet, smart phone, etc.), and supports multiple communication protocols such as Wi-Fi 6, Bluetooth 5.0, 4G / 5G cellular network, Zigbee, etc., to ensure the data transmission speed and security in different network environments. During the data transmission process, it also supports data compression, encryption and other functions to ensure the integrity and privacy of the data.

[0077] The data acquisition sub-device provided in this embodiment further includes: a power supply module 14 and a data storage module 12 .

[0078] The power module 14 stores electrical energy and converts it into working power for each module. It includes a variety of transformer ballast units to provide a stable power supply. It also includes an energy efficiency management unit, which can be used to automatically adjust the power output according to the load of each module, and control each module to enter a low power consumption mode when the load is less than a threshold. It also monitors the power in real time, and reminds the user to replace the battery or charge it when the power is low or the battery needs to be replaced.

[0079] The data storage module 12 supports local and cloud data storage, adopts a distributed database architecture, provides data backup and recovery functions, and ensures data security and integrity.

[0080] Specifically, the collected data is first stored in a local storage device (such as an SD card) for quick access and offline use; at the same time, the data is uploaded to the cloud platform using the communication transmission module 13 (such as Wi-Fi or cellular network) to achieve remote backup and access. The data storage module 12 also has an automatic synchronization function, and when network conditions permit, the local data is uploaded to the cloud according to the set rules.

[0081] The device for evaluating the quality of urban nighttime light environment provided in this embodiment has the following advantages:

[0082] 1. Portability optimized design.

[0083] This embodiment adopts modular design and proposes a miniaturized portable data collection device. The device weighs no more than 1500 grams, is compact, has low power consumption, is easy to carry, and is suitable for outdoor real-time monitoring and mobile data collection in urban night light environments.

[0084] 2. An integrated device for multimodal data acquisition.

[0085] A helmet-type multimodal data acquisition device is designed, which can simultaneously collect human physiological data (such as facial expression images, skin conductance, electrocardiogram), human position data (through GPS and inertial navigation system) and night environment data (such as spectral data, wide-angle camera images, temperature and humidity, wind speed and noise). By optimizing the spatial layout of each module, this embodiment solves the problem of poor synchronization caused by the dispersion of multiple devices and realizes high-precision and high-stability data acquisition. These data are analyzed in real time by the processing module of the device to form a closed loop of data acquisition and feedback.

[0086] 3. Real-time synchronization and anomaly detection of multimodal data.

[0087] Through time synchronization algorithms and data fusion technology, this embodiment achieves millisecond-level synchronization of human physiological data, human position data, and nighttime environmental data. Combined with anomaly detection models based on machine learning, data anomalies (such as signal loss, interference, or equipment failure) can be identified and corrected in real time. At the same time, the acquisition supports wireless data transmission function, and data can be transmitted to remote terminals (such as computers and mobile phones) in real time to ensure the reliability and integrity of data acquisition.

[0088] 4. Interdisciplinary data analysis and evaluation model.

[0089] This embodiment integrates multiple algorithms such as light environment science, psychology, physiology and data science, and combines multimodal physiological signal emotion computing algorithms to achieve the evaluation of night light environment quality, thereby improving the accuracy and efficiency of quality analysis. This embodiment can provide suggestions for optimizing the design of the light environment and form a feedback loop centered on user experience. The integration of multiple disciplines significantly improves the accuracy and scientificity of light environment evaluation and solves the limitations of traditional single-discipline methods.

[0090] Example 2

[0091] like Figure 4 As shown, this embodiment provides a method for evaluating the quality of urban nighttime light environment, including:

[0092] S1: Acquire multimodal data, wherein the multimodal data includes human physiological data, nighttime environment data, and human position data.

[0093] S2: Generate a nighttime light environment-emotional quality evaluation map based on the multimodal data.

[0094] S3: Determine the area type on the night light environment-emotional quality evaluation map according to the emotional state value, wherein the emotional state value is a variable value calculated according to the multimodal data, and the area type includes an abnormal area and a non-abnormal area.

[0095] S4: Evaluate the quality of urban night light environment for different types of areas.

[0096] S3 specifically includes:

[0097] S31: extracting characteristic values ​​according to the human physiological data, taking the characteristic values ​​as input, and calculating the emotional state value using the emotion calculation model.

[0098] S32: Determine whether the emotional state value is abnormal based on the covariate, eliminate the abnormal emotional state value, and use the interpolation algorithm to interpolate the eliminated emotional state value to obtain the processed emotional state value, wherein the ambient temperature, ambient humidity, wind speed and noise in the nighttime environmental data are used as the covariate.

[0099] S33: Generate a nighttime light environment-emotional quality evaluation map according to the processed emotional state value, the human body position data, and the photometric data and city image data in the nighttime environment data.

[0100] S34: performing spatial statistical analysis on the processed emotional state values ​​on the nighttime light environment-emotional quality evaluation map, and determining the area type on the nighttime light environment-emotional quality evaluation map according to the analysis result.

[0101] In order to make those skilled in the art more aware of the specific process of the above-mentioned method for evaluating the quality of urban nighttime light environment in this embodiment, a specific explanation is given below.

[0102] (1) Emotional state value measurement

[0103] Light stimulation acts on the retina through visual and non-visual channels, directly or indirectly affecting people's emotional perception. Urban night scene lighting uses artificial light to reshape the landscape of the city's outdoor public space at night, which also affects people's emotions. There is a certain correlation between the brightness and illumination, color temperature and light color, dynamic and flickering changes, and brightness spatial distribution in the urban light environment and human emotions. Good lighting quality, such as appropriate brightness and color temperature, has a positive effect on people's emotions, while landscape lighting that is too dark, too bright, too colorful or too flashing may cause extreme discomfort to people. This kind of uncomfortable emotional response will be fed back to various physiological indicators of the human body, such as skin electricity, electrocardiogram, breathing, and facial expressions. Therefore, by measuring various physiological indicators, the emotional state of the human body can be obtained through the emotional computing model. Combined with other data of the light environment, real-time evaluation of the urban night space can be achieved.

[0104] Emotion is a complex process involving cognition, feelings, motivation, physical reactions, and movements. In this embodiment, human physiological data is processed using a two-dimensional model of emotion, which simplifies and quantifies emotional reactions through two dimensions: emotional valence and emotional arousal. Emotional valence reflects the degree of individual preference for stimulation, ranging from like to dislike; emotional arousal describes the intensity of emotional excitement, ranging from low excitement to high excitement.

[0105] Heart rate variability can reflect an individual's emotional valence and emotional arousal.

[0106] Skin electrical response can reflect an individual's arousal response to environmental stimuli.

[0107] Facial expression video data can be converted into corresponding values ​​in the two-dimensional model of emotions with the help of existing software.

[0108] Eigenvalue extraction:

[0109] Skin conductance data: The skin conductance level SCL signal was extracted and normalized using the Z-score standardization formula to eliminate individual baseline differences.

[0110] ECG data: Calculate the time domain features (such as standard deviation SDNN, root mean square deviation RMSSD) and frequency domain features (such as low frequency / high frequency power ratio LF / HF) of HRV.

[0111] Facial expression images: The expression classification labels (such as pleasure and disgust) are extracted through image analysis technology, and the expression changes are quantified into a two-dimensional emotional model by combining the facial muscle movement characteristics.

[0112] The extracted feature values ​​are integrated into high-dimensional emotion feature vectors through feature fusion algorithm, and then input into the emotion two-dimensional model through deep learning algorithm to output the two dimensions of emotion valence and arousal.

[0113] Finally, the multimodal emotion calculation results are aligned with the timestamp coordinates to form an emotional state value with temporal and spatial consistency.

[0114] (2) Constructing a nighttime environment dataset

[0115] Photometric data, urban image data, ambient temperature, ambient humidity, wind speed and noise, and GPS location information in human position data are collected and integrated to generate a multidimensional nighttime environmental data set for analysis. Specifically, the collected nighttime environmental parameters such as photometric data, urban image data, ambient temperature, ambient humidity, wind speed and noise are integrated with timestamps and spatial coordinates as indexes and stored in a structured database. GIS tools are used to spatially process the integrated data, generate geographic mapping information, and form a standardized nighttime environmental data set.

[0116] (3) Generate night light environment-emotional quality evaluation map

[0117] The mechanism of the impact of urban light environment on human vision and emotion is complex and can be summarized into two levels. The first is the impact of the essential factors of illumination, including light brightness, spectrum, spatial distribution, action time / duration, etc., which affect human vision, physiology and psychology in the form of light radiation energy; the second is the use of artificial light as a technical means to reshape the complex urban landscape elements to create a nighttime urban landscape. This nightscape is mapped into the human brain through the visual system, and processed by the nervous system responsible for emotional processing in the brain, which makes people have emotional experience. This embodiment collects nighttime environmental data, physiological data of the subjects and human body position data, and generates a model for evaluating the relationship between nighttime light environment and emotions through algorithm processing, which is used to evaluate the quality of urban light environment from the perspective of user emotions. The basic content is as follows.

[0118] Analysis of the relationship between night light environment and multimodal emotion computing: Based on the timestamp, the multimodal emotion computing results are spatially coupled with the night light environment dataset, a spatial mapping model is constructed, and a night light environment-emotional quality evaluation map is generated. The emotional valence and emotional arousal distribution of different locations are marked, and areas with low emotional valence and high emotional arousal are preferentially identified to infer potential night view problem points.

[0119] Covariate anomaly detection: Since significant fluctuations in ambient temperature, ambient humidity, wind speed, and noise may have a potential impact on multi-source emotion values, ambient temperature, ambient humidity, wind speed, and noise are included in the spatial mapping model as covariates to quantify their potential impact effects. First, the abnormal fluctuation time points of the covariates are identified through the mutation point detection algorithm. For the data of the abnormally elevated part of the covariates (temperature, humidity, wind speed, and noise), the data is removed according to actual needs. Finally, the interpolation algorithm is used to spatially continuate the data to generate a distribution map of the emotion state values ​​in geographic space.

[0120] (4) Classification and spatial statistical analysis

[0121] The emotional state values ​​in the night light environment-emotional quality evaluation map were spatially statistically analyzed to identify and locate key areas. Spatial hotspot and cold spot analysis was performed on the arousal dimension and valence dimension of the emotional state value, and the emotional characteristics of different areas were annotated using a spatial statistical method (Getis-Ord Gi*). The focus was on the identification of high arousal and low valence areas, and these areas were defined as "abnormal areas" as key targets in the analysis. These abnormal areas may represent potential night space light environment quality problems or high incidence areas of negative emotional experiences.

[0122] (5) Evaluation and optimization feedback

[0123] For key areas, in-depth analysis is carried out by combining photometric data and urban image data to further make problem assessments and decisions, forming a closed-loop feedback mechanism.

[0124] The evaluation method for the quality of urban nighttime light environment provided in this embodiment can quantify individual emotional states and light environment parameters in real time through the collection and processing of multimodal data, and more objectively and accurately evaluate the impact of the urban nighttime light environment on the individual emotional state, providing a basis for the optimal design of the urban light environment.

[0125] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0126] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A device for evaluating the quality of urban nighttime light environment, characterized in that: The device for evaluating the quality of urban nighttime light environment comprises: Data collection sub-devices and terminals; The data acquisition sub-device is communicatively connected with the terminal; The data acquisition sub-device is used to collect multi-modal data, wherein the multi-modal data includes human physiological data, nighttime environmental data and human position data; The terminal is used to generate a night light environment-emotional quality evaluation map according to the multimodal data, determine the area type on the night light environment-emotional quality evaluation map according to the emotional state value, and evaluate the urban night light environment quality for different types of areas, wherein the emotional state value is a variable value calculated based on the multimodal data, and the area type includes an abnormal area and a non-abnormal area.

2. The device for evaluating the quality of urban nighttime light environment according to claim 1, characterized in that: The terminal comprises: A human physiological data processing module, used to extract characteristic values ​​according to the human physiological data, take the characteristic values ​​as input, and calculate the emotional state value using an emotional computing model; an emotional state value processing module, used to determine whether the emotional state value is abnormal according to covariates, remove abnormal emotional state values, and perform interpolation processing on the removed emotional state values ​​using an interpolation algorithm to obtain processed emotional state values, wherein the ambient temperature, ambient humidity, wind speed and noise in the nighttime environmental data are used as the covariates; A nighttime light environment-emotional quality evaluation map generation module, used to generate a nighttime light environment-emotional quality evaluation map according to the processed emotional state value, the human body position data, and the photometric data and city image data in the nighttime environment data; A region type classification module, used to perform spatial statistical analysis on the processed emotional state values ​​on the nighttime light environment-emotional quality evaluation map, and determine the region type on the nighttime light environment-emotional quality evaluation map according to the analysis result; The evaluation module is used to evaluate the quality of urban night light environment for different types of areas.

3. The device for evaluating the quality of urban nighttime light environment according to claim 1, characterized in that: The data collection sub-device is a wearable helmet, and the data collection sub-device includes: Housing, data acquisition module, data preprocessing module and communication transmission module; The data acquisition module, the data preprocessing module and the communication transmission module are all located on the housing; The data preprocessing module is connected to the data acquisition module and the communication transmission module respectively; The data acquisition module is used to acquire the multimodal data; The data preprocessing module is used to preprocess the multimodal data; The communication transmission module is used to transmit the pre-processed multimodal data to the terminal.

4. The device for evaluating the quality of urban nighttime light environment according to claim 3, characterized in that: The data acquisition module also includes: a human physiological data acquisition unit, a nighttime environment data acquisition unit and a position information acquisition unit; The human physiological data acquisition unit, the nighttime environment data acquisition unit and the position information acquisition unit are all connected to the data preprocessing module; The human physiological data acquisition unit is used to acquire the human physiological data, wherein the human physiological data includes human facial expression images, skin conductance data and electrocardiogram data; The nighttime environment data acquisition unit is used to acquire the nighttime environment data, wherein the nighttime environment data includes photometric data, city image data, ambient temperature, ambient humidity, wind speed and noise, and the photometric data includes spectral data and stroboscopic data; The position information acquisition unit is used to acquire the human body position data.

5. The device for evaluating the quality of urban nighttime light environment according to claim 3, characterized in that: The data preprocessing module also includes an anomaly detection and correction unit and a data synchronization and fusion unit; The anomaly detection and correction unit is connected to the data acquisition module and the data synchronization and fusion unit respectively; The data synchronization and fusion unit is connected to the communication transmission module; The abnormality detection and correction unit is used to identify abnormal conditions of the multimodal data, and perform abnormal correction and alarm, wherein the abnormal conditions include signal loss, data noise and equipment failure; The data synchronization and fusion unit is used to process the corrected multimodal data using a time synchronization algorithm to obtain time-synchronized multimodal data, wherein the time-synchronized multimodal data serves as the preprocessed multimodal data.

6. The device for evaluating the quality of urban nighttime light environment according to claim 3, characterized in that: The data acquisition sub-device also includes: a data storage module; The data storage module is connected to the data acquisition module and the communication transmission module respectively; The data storage module is used to store the pre-processed multimodal data locally and / or in the cloud; the data storage module adopts a distributed database architecture.

7. The device for evaluating the quality of urban nighttime light environment according to claim 3, characterized in that: The data acquisition sub-device also includes: a power supply module; The power supply module is respectively connected to the data acquisition module, the data preprocessing module and the communication transmission module; The power module is used to provide power; The power module also includes an energy efficiency management unit; The energy efficiency management unit is used to automatically adjust the power output according to the load of each module, and control each module to enter a low power consumption mode when the load is less than a threshold; and monitor the power in real time, and remind the user to replace the battery or charge when the power is low or the battery needs to be replaced.

8. The device for evaluating the quality of urban nighttime light environment according to claim 4, characterized in that: The nighttime environment data acquisition unit includes a photometric data measurement sensor, a camera, a temperature sensor, a humidity sensor, a wind speed sensor and a noise sensor.

9. A method for evaluating the quality of urban nighttime light environment, characterized in that: The evaluation method for the quality of urban nighttime light environment includes: Acquiring multimodal data, wherein the multimodal data includes human physiological data, nighttime environmental data, and human position data; generating a nighttime light environment-emotional quality evaluation map according to the multimodal data; Determining the area type on the night light environment-emotional quality evaluation map according to the emotional state value, wherein the emotional state value is a variable value calculated according to the multimodal data, and the area type includes an abnormal area and a non-abnormal area; Evaluate the quality of urban night light environment for different types of areas.

10. The method for evaluating the quality of urban nighttime light environment according to claim 9, characterized in that: Determining the area type on the night light environment-emotional quality evaluation map according to the emotional state value specifically includes: Extracting characteristic values ​​according to the human physiological data, taking the characteristic values ​​as input, and calculating the emotional state value using an emotional computing model; Determining whether the emotional state value is abnormal according to the covariate, eliminating the abnormal emotional state value, and performing interpolation processing on the eliminated emotional state value using an interpolation algorithm to obtain a processed emotional state value, wherein the ambient temperature, ambient humidity, wind speed and noise in the nighttime environmental data are used as the covariate; Generate a nighttime light environment-emotional quality evaluation map according to the processed emotional state value, the human body position data, and the photometric data and city image data in the nighttime environment data; A spatial statistical analysis is performed on the processed emotional state values ​​on the nighttime light environment-emotional quality evaluation map, and a region type on the nighttime light environment-emotional quality evaluation map is determined according to the analysis result.

Images