A method and system for evaluating the impact of high intensity urban street scenes on hedonicity

Abstract

This invention discloses a method and system for assessing the impact of streetscapes in high-intensity urban areas on pleasure levels. It relates to the interdisciplinary fields of data processing and environmental psychology, and includes the following steps: acquiring a target streetscape image and performing semantic segmentation to obtain objective morphological parameters; acquiring eye-tracking physiological data of subjects viewing the target streetscape image and obtaining subjective evaluation data based on the PAD (Patient Affected Observation) emotional scale; classifying the PAD impact type according to the subjective evaluation data; and obtaining two pleasure level correlation scores based on the objective morphological parameters and eye-tracking physiological data; summing the two pleasure level correlation scores to obtain a pleasure level impact correlation value; and using the pleasure level impact correlation value, eye-tracking physiological data, and subjective evaluation data to quantitatively score the impact of the streetscape design on pleasure levels. This invention improves the scientific rigor and accuracy of environmental assessment in high-intensity urban areas by combining objective streetscape indicators, eye-tracking physiological data during subject viewing, and subjective emotional scores.

Description

Technical Field

[0001] This invention relates to the interdisciplinary fields of data processing and environmental psychology, and in particular to a method and system for assessing the impact of high-intensity streetscape on pleasure levels. Background Technology

[0002] In the field of modern urban planning and design, high-intensity urban construction areas have become the core carriers of urban image, not only carrying transportation and commercial functions, but also serving as important spatial media that affect public mental health and emotional well-being.

[0003] However, current technologies for assessing the impact of high-intensity streetscapes on pleasure suffer from several drawbacks. First, existing assessment methods largely rely on single-dimensional data collection and analysis. Traditional methods either collect participants' post-event feelings solely through subjective evaluation questionnaires, which are heavily influenced by participants' memory biases and subjective preferences; or they focus only on physical morphological indicators, lacking real-time capture of physiological and psychological feedback under realistic human-scale experiences. This "mind-body separation" assessment model fails to objectively and accurately reflect the true mechanism by which high-intensity streetscapes induce pleasure in the population. Second, there is a lack of systematic integration of visual perception characteristics and changes in pleasure. In the large-scale spaces of high-intensity areas, the distribution of visual attention is extremely complex. Existing technologies struggle to accurately capture the dynamic correlation between participants' "visual focus" and "pleasure fluctuations" when viewing streetscapes.

[0004] In summary, existing assessment methods mostly rely on single-dimensional data collection, either solely on subjective evaluation questionnaires to collect users' post-event feelings, which are heavily influenced by memory bias and subjective preferences, or focusing only on physical morphological indicators (such as building density and street height-to-width ratio). This "mind-body separation" assessment model makes it impossible to establish a systematic quantitative correlation between objective streetscape morphological characteristics and actual changes in people's pleasure levels, and it is difficult to accurately reveal the impact mechanism of high-intensity urban street environments on pleasure levels. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of the prior art by providing a method and system for evaluating the impact of high-intensity streetscape on pleasure levels, thereby solving the problems in the prior art.

[0006] The present invention specifically provides the following technical solution: A method for assessing the impact of high-intensity street view on pleasantness includes: Acquire target street view images of the high-intensity street units to be evaluated; wherein the high-intensity areas represent high-density development environments. Semantic segmentation is performed on the target street view image to obtain objective morphological parameters including the richness of street-side elements and the undulation of high-rise buildings along the street; eye-tracking physiological data of the subject when viewing the target street view image and subjective evaluation data of the subject after viewing based on the PAD emotion scale are obtained. Based on subjective evaluation data, the pleasure level P in the PAD emotional scale was identified as the dominant influence type, and the arousal level A and dominance level D in the PAD emotional scale were identified as subordinate influence types. Under objective morphological parameters and eye movement physiological data, the target eye movement features of the dominant and subordinate influence types were extracted respectively. The weighted sums of each target eye movement feature were accumulated to obtain the first pleasure level correlation score and the second pleasure level correlation score. The pleasure level influence correlation value was obtained by weighting the first pleasure level correlation score and the second pleasure level correlation score. Based on the aforementioned pleasure level impact correlation value, eye movement physiological data, and subjective evaluation data, a quantitative score is generated for the impact of the street view scheme corresponding to the target street view image on pleasure level.

[0007] Preferably, under the objective morphological parameters and eye-tracking physiological data, the index scores of the dominant influence type and the subordinate influence type are extracted respectively, and the scores of all indicators in the objective morphological parameters and eye-tracking physiological data are accumulated to obtain the first pleasure correlation total score and the second pleasure correlation total score, specifically as follows: Target eye movement features related to pleasure level P are selected from objective morphological parameters, and the weight of each target eye movement feature is determined. The weights are then weighted with the measured values ​​of each target eye movement feature to obtain the total score of the first indicator. Target eye movement features related to arousal A and dominance D are selected from objective morphological parameters, and the weights related to arousal A and dominance D are determined respectively. The weights are then weighted with the measured values ​​of each target eye movement feature to obtain the sum of the second index scores. The first pleasure-related total score is determined based on the sum of the first index scores and the sum of the second index scores. Based on the target eye movement features in the eye movement physiological data, the first pleasure-related total score in the objective morphological parameters is obtained. Then, the sum of the scores of the third related indicators corresponding to the core influence type and the sum of the scores of the fourth related indicators corresponding to the auxiliary influence type are obtained respectively. The second pleasure-related total score is determined based on the sum of the scores of the third and fourth related indicators.

[0008] Preferably, the extraction of target eye-tracking features for the dominant influence type and the subordinate influence type specifically includes: Based on the subjective evaluation data, all emotion classification scores under the dimensions of pleasure (P), arousal (A), and dominance (D) were obtained, and the arithmetic mean of all emotion classification scores under different dimensions was taken as the emotion classification score of each subject on the stimulus. Based on each subject's emotion classification score on the stimulus, the average score of each emotion classification for all subjects on the PAD Emotion Scale was determined; Based on the aforementioned eye movement physiological data, eye movement indicators were extracted for each subject during stimulus presentation to determine the eye movement characteristics of each subject. These eye movement characteristics included average pupil diameter, average fixation duration, number of fixations, and average number of blinks. Average pupil diameter reflected arousal level (A), while average fixation duration and number of fixations reflected dominance level (D). The positive correlation between arousal level (A) and pleasure level (P) was used to obtain the pleasure level. A decrease in the average number of blinks was negatively correlated with an increase in pleasure level. Based on each subject's eye movement feature, each emotion category score, and the average of each emotion category score, the Pearson correlation coefficient between each emotion category and each eye movement feature is determined, and the target eye movement feature that is associated with the emotion category is determined based on the Pearson correlation coefficient.

[0009] Preferably, based on subjective evaluation data, the pleasure level P in the PAD emotional scale is determined as the dominant influence type, and the arousal level A and dominance level D in the PAD emotional scale are determined as subordinate influence types, specifically as follows: By obtaining the Euclidean distance between the subject's PAD score and the basic emotional type, the degree of the subject's emotional tendency and the basic emotional tendency are obtained. The emotional type that is closest to the subject's emotional state is considered as the subject's PAD emotional tendency, and the influence type of PAD is classified according to the PAD emotional tendency.

[0010] Preferably, a quantitative score of the impact of the street view scheme corresponding to the target street view image on the level of pleasure is generated based on the pleasure impact correlation value, eye-tracking physiological data, and subjective evaluation data, specifically as follows: Based on the eye-tracking physiological data, a first indicator reflecting the attention given to the street view solution is obtained; Based on the aforementioned pleasure level impact correlation value, a second indicator is obtained regarding the impact of the street view scheme on pleasure level changes; Subjective evaluation data of subjects after viewing the target street view image is obtained as a third indicator to characterize the degree of matching between the street view scheme and the spatial environment; The quantitative score is generated based on the preset weights of the first, second, and third indicators.

[0011] Preferably, the first indicator reflecting the attention given to the street view solution specifically includes: Acquire the gaze trajectory of the subject while viewing the target street view image; The average fixation duration, pupil diameter change, number of fixations, and first fixation duration of the subjects were obtained for each region in the target street view image. The average fixation duration, pupil diameter variation, number of fixations, and duration of first fixation for each region were normalized. A weighted summation model was then used to sum the normalized average fixation duration, pupil diameter variation, and number of fixations to determine the primary indicator reflecting the attention given to the street view solution.

[0012] Preferably, after generating a quantitative score of the impact of the street view scheme corresponding to the target street view image on the pleasure level, the method further includes evaluating and ranking all street view schemes, and selecting the optimal street view scheme, specifically: Obtain quantitative scores of the relative costs and impact on user experience of implementing multiple different street view solutions; Obtain the street width of the target street view image, calculate the street aspect ratio based on the street width, and classify different street view morphology types based on the street aspect ratio; Based on the weights of each street view element index in different street view morphology types, the street view element indexes of each street view scheme are scored, and all scores are summed to obtain the comprehensive feasibility score of each street view scheme. Based on the quantitative score, comprehensive feasibility score, and relative cost, multiple street view schemes are comprehensively evaluated and ranked, and the optimal street view scheme is selected.

[0013] Preferably, the step of comprehensively evaluating and ranking multiple street view schemes to select the optimal street view scheme specifically includes: Each street view scheme is evaluated to obtain a quantitative score, and the highest quantitative score among all street view schemes is determined. If the highest value of the quantitative score is greater than zero, the ratio of the quantitative score of each street view scheme to the highest value of the quantitative score is used as the score ratio of each scheme. The relative cost is normalized to obtain the target relative cost; Assign weight values ​​to the quantitative score, relative cost, and implementation feasibility score respectively; Based on the weight values, scoring ratios, target relative costs, and implementation feasibility scores, a comprehensive score for each street view scheme is obtained and ranked, and the optimal street view scheme is selected.

[0014] Preferably, the element richness refers to the density of visual information, physical spatial entities, spatial structures and content contained in the target street view image; the undulation of the high-rise buildings along the street refers to the overall fluctuation range of the urban building outline in the horizontal and vertical directions, reflecting the intensity of the building height or outline undulation.

[0015] This invention provides a system for evaluating the impact of high-intensity streetscape on pleasantness, comprising: The first acquisition unit is used to acquire target street view images of high-intensity street units to be evaluated; wherein the high-intensity area represents a high-density development environment area. The second acquisition unit is used to perform semantic segmentation on the target street view image, and acquire objective morphological parameters including the richness of street-side elements and the undulation of high-rise buildings along the street; acquire eye-tracking physiological data of the subject when viewing the target street view image and subjective evaluation data of the subject after viewing based on the PAD emotion scale; The third acquisition unit is used to determine the pleasure level P in the PAD emotional scale as the dominant influence type and the arousal level A and dominance level D in the PAD emotional scale as subordinate influence types based on subjective evaluation data. Under objective morphological parameters and eye movement physiological data, the target eye movement features of the dominant influence type and subordinate influence type are extracted respectively. The weighted sums of each target eye movement feature are accumulated to obtain the first pleasure level association total score and the second pleasure level association total score. The pleasure level influence association value is obtained by weighting the first pleasure level association total score and the second pleasure level association total score. The quantitative scoring unit is used to generate a quantitative score of the impact of the street view scheme corresponding to the target street view image on the level of pleasure based on the pleasure impact correlation value, eye movement physiological data and subjective evaluation data.

[0016] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a program, and when the program is executed by the processor, the processor performs the steps of the above-described method for evaluating the impact of high-intensity street view on pleasantness.

[0017] The present invention provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method for evaluating the impact of high-intensity street view on pleasantness.

[0018] Compared with the prior art, the present invention has the following significant advantages: This invention targets high-intensity street scene sample images, acquiring objective morphological parameters, eye-tracking physiological data, and subjective evaluation data. These three types of data serve as the foundation for subsequent pleasure scoring, comprehensively and objectively revealing the true induction mechanism of high-intensity street environments on human pleasure. Furthermore, eye-tracking technology is used to obtain real-time physiological feedback from subjects viewing street scene images, combined with subjective evaluations from the PAD emotional scale, quantifying the scores of different influence types. This allows for the precise establishment of a mapping relationship between visual attention distribution and changes in emotional pleasure, achieving a refined and dynamic analysis of human psychological feelings. For the first time, a systematic quantitative correlation between the morphological characteristics of high-intensity street scenes and changes in human pleasure has been established at a human-centric scale, thus objectively and accurately revealing the true induction mechanism of street scene schemes on pleasure. Attached Figure Description

[0019] Figure 1This is a flowchart illustrating a method for evaluating the impact of streetscape in high-intensity urban areas on pleasure levels, provided by the present invention. Figure 2 This is a schematic diagram of a street scene semantic segmentation result provided by the present invention; wherein, Figure 2 (a)- Figure 2 (l) represent different street scene semantic segmentation results; Figure 3 This is a schematic diagram of the heat map collected by the present invention; wherein, Figure 3 (a)- Figure 3 (l) are heat maps of different street scenes; Figure 4 This is a schematic diagram of PAD sentiment value scoring for street view target images provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] Appendix Figure 1 This embodiment illustrates the overall technical implementation flowchart. The method for evaluating the impact of high-intensity streetscape on pleasantness in this embodiment includes: Step 1: Obtain target street view images of the high-intensity street units to be evaluated and group them by aspect ratio; where high-intensity areas represent high-density development environments.

[0022] The image contains visual information such as the ground along the street, buildings on both sides of the street, and the sky. For the target street view image, the street width is first calculated, and then the street width-to-height ratio is calculated to obtain the street view morphology type classification (street width - street height-to-width ratio (subclass), forming the subclass of street view morphology type).

[0023] Step 2: Perform semantic segmentation on the grouped target street view images to obtain objective morphological parameters, including at least street view element richness (x) and the undulation of tall buildings along the street (z). Obtain eye-tracking physiological data of the subjects while viewing the target street view images using eye-tracking technology, and obtain the subjects' subjective evaluation data after viewing using the PAD sentiment scale.

[0024] Feature richness refers to the density of visual information, physical entities, spatial structures, and content contained in a target street view image; that is, the number of street view feature types contained in the target street view image. After image semantic segmentation, the number of feature types in each target street view image is counted and manually corrected to obtain the feature richness of different target street view images; that is, feature richness = number of environmental feature types in the target street view image. The undulation of high-rise buildings along the street refers to the overall fluctuation range of the urban building outline in the horizontal (X-axis) and vertical (Y-axis) directions, reflecting the intensity of building height or outline undulation. A smaller value indicates a relatively gentle change in the building, while a larger value indicates a more dramatic change in building undulation. The formula is as follows: ; Where B represents the undulation of the high-rise buildings along the street. This represents the average gradient in the horizontal direction, i.e., the degree of lateral variation within the building complex. The mean gradient in the vertical direction represents the degree of variation in building height. The semantic segmentation results are as follows: Figure 2 As shown.

[0025] Before constructing the pleasure assessment model based on objective morphological parameters, eye movement physiological data, and PAD emotional scale data, the method also includes: obtaining all emotion category scores under the dimensions of pleasure (P), arousal (A), and dominance (D) based on subjective evaluation data, and taking the arithmetic mean of all emotion category scores under different dimensions as the emotion category score for each subject on the stimulus; determining the average score of each subject's emotion category score on the PAD emotional scale based on the emotion category score for each subject on the stimulus; and extracting eye movement indicators for each subject during stimulus presentation based on eye movement physiological data to determine the eye movement characteristics of each subject, including average pupil diameter, average fixation duration, fixation frequency, and average blink frequency. Among these, pupil diameter is used to measure an individual's cognitive load and emotional activation state. Key indicators include average pupil diameter, pupil diameter change rate, and pupillary reaction time. Pupil dilation usually indicates a high cognitive load, such as when facing complex tasks or stimulating environments, while pupil constriction reflects a possible relaxed state. Fixation metrics: These metrics assess an individual's intensity of attention and depth of information processing for a specific area. Key metrics include fixation duration, total fixation time, and number of fixations. Longer fixation duration generally indicates higher information complexity in the area, requiring more time to understand, while a higher number of fixations suggests stronger visual appeal. Blinking metrics: These metrics assess visual fatigue and cognitive load by measuring an individual's blinking frequency and duration. Key metrics include average blink count, blink duration, and blink frequency. A low blink rate typically indicates high concentration, while a high blink rate may indicate visual fatigue or cognitive overload. In this invention, average pupil diameter reflects arousal level (A), and fixation frequency reflects dominance (D). The positive correlation between arousal level (A) and pleasure level (P) is used to obtain the pleasure level, while a decrease in average fixation duration is negatively correlated with an increase in pleasure level. Based on the scores of each eye movement feature, each emotion category, and the average score of each emotion category for each subject, the Pearson correlation coefficient between each emotion category and each eye movement feature is determined. The target eye movement features associated with the emotion category are determined based on the Pearson correlation coefficient. In one embodiment, at least one target emotion category and at least one target eye movement feature are determined, and at least one target emotion category and at least one target eye movement feature have a significant correlation. Schematic diagrams of different collected heatmaps are shown below. Figure 3 As shown.

[0026] Step 3: Based on subjective evaluation data, the pleasure level P in the PAD emotional scale is identified as the dominant influence type, and the arousal level A and dominance level D in the PAD emotional scale are identified as subordinate influence types. Under objective morphological parameters and eye movement physiological data, the target eye movement features of the dominant and subordinate influence types are extracted respectively. The weighted sums of each target eye movement feature are accumulated to obtain the first pleasure level correlation score and the second pleasure level correlation score. The pleasure level influence correlation value is obtained by weighting the first pleasure level correlation score and the second pleasure level correlation score.

[0027] After obtaining the relevant relationships, the PAD score based on the basic emotion type can be used to assess the subject's emotional tendency. By calculating the Euclidean distance between the subject's PAD score and the basic emotion type, the degree of the subject's emotional tendency can be determined. The emotion type that is closest to the subject's emotional state is considered the subject's PAD emotional tendency. The calculation formula is as follows: ; In the formula L m P represents the coordinate distance between the subject's emotional state and basic emotional type in the PAD emotional model, where P, A, and D are the coordinates of the subject's three emotional dimensions, respectively. p m , a m , d m The coordinates are the basic emotion types, m=[1,14].

[0028] According to the method for assessing the impact of high-intensity street view on pleasure provided by the present invention, a pleasure assessment model is constructed based on objective morphological parameters, eye movement physiological data, and PAD emotional scale data. The model includes: determining pleasure level P as the dominant influence type and arousal level A and dominance level D as subordinate influence types based on PAD emotional tendency; selecting target eye movement features related to pleasure level P from the objective morphological parameters and determining the weights of the target eye movement features; obtaining the sum of the first index scores by weighting the weights with the measured values ​​of the target eye movement features; and selecting target eye movement features related to arousal level A and dominance level D from the objective morphological parameters. The target eye-movement features are analyzed, and the weights related to arousal (A) and dominance (D) are determined. The weights are then weighted with the measured values ​​of the target eye-movement features to obtain the sum of the second indicator scores. The first pleasure-related total score is determined based on the sum of the first and second indicator scores. The third and fourth related indicator scores corresponding to the core influence types are obtained based on eye-movement physiological data. The second pleasure-related total score is obtained based on the sum of the third and fourth related indicator scores. The pleasure-related influence value is obtained based on the first and second pleasure-related total scores.

[0029] Step 4: Generate a quantitative score of the impact of the street view scheme corresponding to the target street view image on the level of pleasure based on the pleasure impact correlation value, eye movement physiological data, and subjective evaluation data.

[0030] A quantitative score on the impact of street view solutions on pleasure is generated based on objective morphological parameters, eye-tracking physiological data, and pleasure-related correlation values. This includes: obtaining a first indicator reflecting the attention given to the street view solution based on eye-tracking physiological data; obtaining a second indicator on the impact of the street view solution on pleasure-related changes based on pleasure-related correlation values; obtaining subjective evaluation data of subjects after viewing the target street view image as a third indicator representing the degree of matching between the street view solution and the spatial environment; and generating a quantitative score on the impact on pleasure based on the preset weights of the first, second, and third indicators.

[0031] To obtain the primary indicator reflecting the visual appeal of the street view solution, the following methods were employed: obtaining the gaze trajectory of subjects viewing street view sample images; obtaining the average gaze duration, pupil diameter change, number of gazes, and first gaze duration of subjects in each region (vegetation region, building region, pedestrian space region, etc.) of the street view sample images; normalizing the average gaze duration, pupil diameter change, number of gazes, and first gaze duration of each region, and summing the normalized average gaze duration, pupil diameter change, and number of gazes using a weighted summation model to determine the primary indicator reflecting the attention given to the street view solution; wherein, the weights of the weighted summation model were calibrated using the analytic hierarchy process (AHP).

[0032] After generating a quantitative score for the impact of the street view scheme corresponding to the target street view image on the level of pleasure, the process also includes evaluating and ranking all street view schemes, and selecting the optimal street view scheme, specifically: The system obtains quantitative scores on the relative costs and impact on user experience of implementing multiple different street view solutions. Based on the weights of each street view element index in different street view types, it scores the street view element indexes of each solution and sums all scores to obtain the comprehensive feasibility score for each solution. Based on the quantitative scores, implementation feasibility scores, and relative costs, the system comprehensively evaluates and ranks the multiple street view solutions and selects the optimal solution.

[0033] Multiple street view solutions are comprehensively evaluated and ranked to select the optimal solution. This process includes: obtaining a quantitative score for each solution and determining the highest quantitative score among all solutions; if the highest quantitative score is greater than zero, the ratio of the quantitative score to the highest quantitative score is used as the score ratio for each solution; normalizing the relative cost to obtain the target relative cost; assigning weights to the quantitative score, relative cost, and feasibility score; and obtaining and ranking the comprehensive score of each street view solution based on the weights, score ratio, target relative cost, and feasibility score, ultimately selecting the optimal solution. The PAD sentiment value of the target street view image is analyzed as follows: Figure 4 As shown.

[0034] Pleasure levels can be categorized using multiple adjective pairs that share a common characteristic, for example: The PAD scale can be shown as follows: Table 1 PAD Scale

[0035] Based on the above method, this invention proposes a system for evaluating the impact of high-intensity street view on pleasure level, comprising: a first acquisition unit, a second acquisition unit, a third acquisition unit, and a quantitative scoring unit.

[0036] The system comprises three main components: a first acquisition unit for acquiring target street view images of high-intensity street units to be evaluated (where high-intensity areas represent high-density development environments); a second acquisition unit for semantic segmentation of the target street view images to acquire objective morphological parameters including the richness of street-side elements and the undulation of high-rise buildings along the street; acquisition of eye-tracking physiological data of subjects viewing the target street view images; and acquisition of subjective evaluation data of subjects after viewing the images based on the PAD emotional scale. A third acquisition unit, based on the subjective evaluation data, identifies the pleasure level P in the PAD emotional scale as the dominant influence type and further refines the PAD emotional scale. In the table, arousal level A and dominance level D are identified as subordinate influence types. Under objective morphological parameters and eye movement physiological data, target eye movement features for the dominant and subordinate influence types are extracted respectively. The weighted sums of each target eye movement feature are accumulated to obtain the first pleasure correlation total score and the second pleasure correlation total score. The pleasure influence correlation value is obtained by weighting the first pleasure correlation total score and the second pleasure correlation total score. The quantitative scoring unit is used to generate a quantitative score of the influence of the street view scheme corresponding to the target street view image on pleasure based on the pleasure influence correlation value, eye movement physiological data, and subjective evaluation data.

[0037] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a program, and when the program is executed by the processor, the processor performs the steps of a method for evaluating the impact of high-intensity street view on pleasure.

[0038] According to the disclosed embodiments, the computer device can communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth communication, etc.) or with any device that enables the computing device to communicate with one or more other computing devices (e.g., router, demodulator, etc.).

[0039] The present invention also provides a storage medium storing a computer program thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of a method for evaluating the impact of high-intensity street view on pleasantness.

[0040] According to the disclosed embodiments, the storage medium can be a non-volatile computer-readable storage medium, such as, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, the storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0041] The above description, in conjunction with specific preferred embodiments, provides a more detailed explanation of the present invention. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such deductions or substitutions should be considered to fall within the scope of protection of the present invention.

Claims

1. A method for evaluating the impact of high-intensity streetscape on pleasantness, characterized in that, Includes the following steps: Acquire target street view images of the high-intensity street units to be evaluated; wherein the high-intensity areas represent high-density development environments. Semantic segmentation is performed on the target street view image to obtain objective morphological parameters including the richness of street-side elements and the undulation of high-rise buildings along the street; eye-tracking physiological data of the subject when viewing the target street view image and subjective evaluation data of the subject after viewing based on the PAD emotion scale are obtained. Based on subjective evaluation data, the pleasure level P in the PAD emotional scale was identified as the dominant influence type, and the arousal level A and dominance level D in the PAD emotional scale were identified as subordinate influence types. Under objective morphological parameters and eye movement physiological data, the target eye movement features of the dominant and subordinate influence types were extracted respectively. The weighted sums of each target eye movement feature were accumulated to obtain the first pleasure level correlation score and the second pleasure level correlation score. The pleasure level influence correlation value was obtained by weighting the first pleasure level correlation score and the second pleasure level correlation score. Based on the aforementioned pleasure level impact correlation value, eye movement physiological data, and subjective evaluation data, a quantitative score is generated for the impact of the street view scheme corresponding to the target street view image on pleasure level.

2. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 1, characterized in that, The method involves extracting the index scores for the dominant and subordinate influence types under objective morphological parameters and eye-tracking physiological data, respectively. The scores of all indicators from both the objective morphological parameters and eye-tracking physiological data are then summed to obtain the first and second pleasure-related total scores. Specifically: Target eye movement features related to pleasure level P are selected from objective morphological parameters, and the weight of each target eye movement feature is determined. The weights are then weighted with the measured values ​​of each target eye movement feature to obtain the total score of the first indicator. Target eye movement features related to arousal A and dominance D are selected from objective morphological parameters, and the weights related to arousal A and dominance D are determined respectively. The weights are then weighted with the measured values ​​of each target eye movement feature to obtain the sum of the second index scores. The first pleasure-related total score is determined based on the sum of the first index scores and the sum of the second index scores. Based on the target eye movement features in the eye movement physiological data, the first pleasure-related total score in the objective morphological parameters is obtained. Then, the sum of the scores of the third related indicators corresponding to the core influence type and the sum of the scores of the fourth related indicators corresponding to the auxiliary influence type are obtained respectively. The second pleasure-related total score is determined based on the sum of the scores of the third and fourth related indicators.

3. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 2, characterized in that, The extraction of target eye-tracking features for the dominant and subordinate influence types is specifically as follows: Based on the subjective evaluation data, all emotion classification scores under the dimensions of pleasure (P), arousal (A), and dominance (D) were obtained, and the arithmetic mean of all emotion classification scores under different dimensions was taken as the emotion classification score of each subject on the stimulus. Based on each subject's emotion classification score on the stimulus, the average score of each emotion classification for all subjects on the PAD Emotion Scale was determined; Based on the eye movement physiological data, eye movement indicators for each subject during stimulus presentation were extracted to determine the eye movement characteristics of each subject; The eye movement characteristics mentioned include average pupil diameter, average fixation duration, number of fixations, and average number of blinks; Arousal level (A) was reflected by average pupil diameter, and dominance level (D) was reflected by average fixation duration and fixation frequency. The level of pleasure was obtained by combining the positive correlation between arousal level (A) and pleasure level (P). A decrease in average blink frequency was negatively correlated with an increase in pleasure level. Based on each subject's eye movement feature, each emotion category score, and the average of each emotion category score, the Pearson correlation coefficient between each emotion category and each eye movement feature is determined, and the target eye movement feature that is associated with the emotion category is determined based on the Pearson correlation coefficient.

4. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 1, characterized in that, Based on subjective evaluation data, the pleasure level (P) in the PAD emotional scale is identified as the dominant influence type, and the arousal level (A) and dominance level (D) in the PAD emotional scale are identified as subordinate influence types, specifically as follows: By obtaining the Euclidean distance between the subject's PAD score and the basic emotional type, the degree of the subject's emotional tendency and the basic emotional tendency are obtained. The emotional type that is closest to the subject's emotional state is considered as the subject's PAD emotional tendency, and the influence type of PAD is classified according to the PAD emotional tendency.

5. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 1, characterized in that, Based on the aforementioned pleasure level impact correlation value, eye-tracking physiological data, and subjective evaluation data, a quantitative score is generated for the impact of the street view scheme corresponding to the target street view image on pleasure level, specifically as follows: Based on the eye-tracking physiological data, a first indicator reflecting the attention given to the street view solution is obtained; Based on the aforementioned pleasure level impact correlation value, a second indicator is obtained regarding the impact of the street view scheme on pleasure level changes; Subjective evaluation data of subjects after viewing the target street view image is obtained as a third indicator to characterize the degree of matching between the street view scheme and the spatial environment; The quantitative score is generated based on the preset weights of the first, second, and third indicators.

6. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 5, characterized in that, The first indicator for obtaining the attention given to the street view solution is specifically: Acquire the gaze trajectory of the subject while viewing the target street view image; The average fixation duration, pupil diameter change, number of fixations, and first fixation duration of the subjects were obtained for each region in the target street view image. The average fixation duration, pupil diameter variation, number of fixations, and duration of first fixation for each region were normalized. A weighted summation model was then used to sum the normalized average fixation duration, pupil diameter variation, and number of fixations to determine the primary indicator reflecting the attention given to the street view solution.

7. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 1, characterized in that, After generating a quantitative score for the impact of the street view scheme corresponding to the target street view image on the user's enjoyment level, the process also includes evaluating and ranking all street view schemes to select the optimal one. Specifically: Obtain quantitative scores of the relative costs and impact on user experience of implementing multiple different street view solutions; Obtain the street width of the target street view image, calculate the street aspect ratio based on the street width, and classify different street view morphology types based on the street aspect ratio; Based on the weights of each street view element index in different street view morphology types, the street view element indexes of each street view scheme are scored, and all scores are summed to obtain the comprehensive feasibility score of each street view scheme. Based on the quantitative score, comprehensive feasibility score, and relative cost, multiple street view schemes are comprehensively evaluated and ranked, and the optimal street view scheme is selected.

8. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 7, characterized in that, The process of comprehensively evaluating and ranking multiple street view schemes to select the optimal street view scheme specifically includes: Each street view scheme is evaluated to obtain a quantitative score, and the highest quantitative score among all street view schemes is determined. If the highest value of the quantitative score is greater than zero, the ratio of the quantitative score of each street view scheme to the highest value of the quantitative score is used as the score ratio of each scheme. The relative cost is normalized to obtain the target relative cost; Assign weight values ​​to the quantitative score, relative cost, and implementation feasibility score respectively; Based on the weight values, scoring ratios, target relative costs, and implementation feasibility scores, a comprehensive score for each street view scheme is obtained and ranked, and the optimal street view scheme is selected.

9. The method for evaluating the impact of high-intensity streetscape on pleasantness as described in claim 1, characterized in that, The element richness refers to the density of visual information, physical spatial entities, spatial structures and content contained in the target street view image; the undulation of high-rise buildings along the street refers to the overall fluctuation range of the urban building outline in the horizontal and vertical directions, reflecting the intensity of the building height or outline undulation.

10. A system for evaluating the impact of high-intensity streetscape on pleasantness, characterized in that, include: The first acquisition unit is used to acquire target street view images of the high-intensity area street units to be evaluated; The high-intensity areas refer to high-density development environment areas; The second acquisition unit is used to perform semantic segmentation on the target street view image, and acquire objective morphological parameters including the richness of street-side elements and the undulation of high-rise buildings along the street; acquire eye-tracking physiological data of the subject when viewing the target street view image and subjective evaluation data of the subject after viewing based on the PAD emotion scale; The third acquisition unit is used to determine the pleasure level P in the PAD emotional scale as the dominant influence type and the arousal level A and dominance level D in the PAD emotional scale as subordinate influence types based on subjective evaluation data. Under objective morphological parameters and eye movement physiological data, the target eye movement features of the dominant influence type and subordinate influence type are extracted respectively. The weighted sums of each target eye movement feature are accumulated to obtain the first pleasure level association total score and the second pleasure level association total score. The pleasure level influence association value is obtained by weighting the first pleasure level association total score and the second pleasure level association total score. The quantitative scoring unit is used to generate a quantitative score of the impact of the street view scheme corresponding to the target street view image on the level of pleasure based on the pleasure impact correlation value, eye movement physiological data and subjective evaluation data.

Images