Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869116
Yao–Ming Zhang, S. Lin, Tzu-Hsiang Chou, Sin-Ye Jhong, Yung-Yao Chen
Lane detection is an important topic in the self-driving system. Having a stable lane detection system will assist the self-driving cars to make decisions in order to bring a more comfortable and safe driving environment to the driver. In this paper, we use a network architecture composed of Encoder-Decoder with a Feature Shift Aggregator between them to make the prediction more comprehensive; through our dataset, we found that some problems such as glitches occur when changing lanes. In this regard, we use Data Augmentation and Filter respectively to solve the problem. Finally, the network achieves the result accuracy rate of SOTA on the TuSimple dataset.
{"title":"Robust Lane Detection via Filter Estimator and Data Augmentation","authors":"Yao–Ming Zhang, S. Lin, Tzu-Hsiang Chou, Sin-Ye Jhong, Yung-Yao Chen","doi":"10.1109/ICCE-Taiwan55306.2022.9869116","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869116","url":null,"abstract":"Lane detection is an important topic in the self-driving system. Having a stable lane detection system will assist the self-driving cars to make decisions in order to bring a more comfortable and safe driving environment to the driver. In this paper, we use a network architecture composed of Encoder-Decoder with a Feature Shift Aggregator between them to make the prediction more comprehensive; through our dataset, we found that some problems such as glitches occur when changing lanes. In this regard, we use Data Augmentation and Filter respectively to solve the problem. Finally, the network achieves the result accuracy rate of SOTA on the TuSimple dataset.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"69 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123247444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869054
Wen-Hui Chen, H. Hsu, Yu‐Chen Lin
Potholes or uneven road surfaces can lead to flat tires, suspension damage, or even accidents. A real-time uneven pavement detection system can provide drivers with information beforehand to reduce car damage and safety risk. It also can be used to inform road repair and maintenance departments to save the efforts of manual inspection. The proposed real-time detection system employs the YOLO-v4 algorithm as the detection model followed by quantization using the Vitis-AI framework for model compression so that the developed system can be performed on the Xilinx FPGA platform without compromising on accuracy and speed. Experimental results show that the proposed system can obtain 28 FPS with four-thread running at 300 MHz.
{"title":"Implementation of a Real-time Uneven Pavement Detection System on FPGA Platforms","authors":"Wen-Hui Chen, H. Hsu, Yu‐Chen Lin","doi":"10.1109/ICCE-Taiwan55306.2022.9869054","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869054","url":null,"abstract":"Potholes or uneven road surfaces can lead to flat tires, suspension damage, or even accidents. A real-time uneven pavement detection system can provide drivers with information beforehand to reduce car damage and safety risk. It also can be used to inform road repair and maintenance departments to save the efforts of manual inspection. The proposed real-time detection system employs the YOLO-v4 algorithm as the detection model followed by quantization using the Vitis-AI framework for model compression so that the developed system can be performed on the Xilinx FPGA platform without compromising on accuracy and speed. Experimental results show that the proposed system can obtain 28 FPS with four-thread running at 300 MHz.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125720384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869177
Aris S. Canto, Pedro V.S. Matias, Rafael O. Moreira, Thyago A. Sampaio, Adriano E. Santos, D. F. Luiz, Celso B. Carvalho, W. S. S. Júnior
Due to the increasing number of drivers on the highways, we are exposed to an increasing probability of acci-dents. Collisions between vehicles can cause serious health and economic problems. In this work, we propose a system that uses a set of sensors, a microcontroller and a mobile application (Android) to notify emergency contacts and to inform the location of the accident. We define range metrics that prevent and indicate possible safety zones (safe, alert and danger). Additionally, we perform collision and rollover estimation of the vehicle. Finally, it sends reports with data from the events generated during the vehicle traffic. In terms of results, it was found that the performance is adequate for the proposed application.
{"title":"A mobile IoT system for the detection and prevention of vehicular collisions","authors":"Aris S. Canto, Pedro V.S. Matias, Rafael O. Moreira, Thyago A. Sampaio, Adriano E. Santos, D. F. Luiz, Celso B. Carvalho, W. S. S. Júnior","doi":"10.1109/ICCE-Taiwan55306.2022.9869177","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869177","url":null,"abstract":"Due to the increasing number of drivers on the highways, we are exposed to an increasing probability of acci-dents. Collisions between vehicles can cause serious health and economic problems. In this work, we propose a system that uses a set of sensors, a microcontroller and a mobile application (Android) to notify emergency contacts and to inform the location of the accident. We define range metrics that prevent and indicate possible safety zones (safe, alert and danger). Additionally, we perform collision and rollover estimation of the vehicle. Finally, it sends reports with data from the events generated during the vehicle traffic. In terms of results, it was found that the performance is adequate for the proposed application.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125724905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869288
Tzu-Hsuan Yeh, Saiau-Yue Tsau
Facial expressions are an essential part of the communication channel for humans, so people's eyes will focus on facial expressions when talking [1]. This research has provided a cat-ear animated accessory to help Virtual Youtuber solve the stone face problem and insufficient emotional communication.
{"title":"Taking Cat Ears to Improve the Facial Emotions of Virtual YouTuber to Enhance the Immersion of Readers","authors":"Tzu-Hsuan Yeh, Saiau-Yue Tsau","doi":"10.1109/ICCE-Taiwan55306.2022.9869288","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869288","url":null,"abstract":"Facial expressions are an essential part of the communication channel for humans, so people's eyes will focus on facial expressions when talking [1]. This research has provided a cat-ear animated accessory to help Virtual Youtuber solve the stone face problem and insufficient emotional communication.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125183052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869123
Y. Ishibashi, Jianlin Ma, K. Psannis
In this paper, we examine effects of haptic and visual senses on human angle perception for networked virtual environments by QoE (Quality of Experience) assessment. Each subject can touch angles in a 3D virtual space through a haptic interface device as well as watching them. By making a comparison among three cases, we clarify each effect of the two senses. One case uses only haptic sense, another case employs only visual sense, and the other case utilizes both senses. As a result, we can quantitatively confirm that the visual sense can differentiate angles more easily than the haptic sense.
{"title":"Effects of Haptic and Visual Senses on Angle Perception for Networked Virtual Environments","authors":"Y. Ishibashi, Jianlin Ma, K. Psannis","doi":"10.1109/ICCE-Taiwan55306.2022.9869123","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869123","url":null,"abstract":"In this paper, we examine effects of haptic and visual senses on human angle perception for networked virtual environments by QoE (Quality of Experience) assessment. Each subject can touch angles in a 3D virtual space through a haptic interface device as well as watching them. By making a comparison among three cases, we clarify each effect of the two senses. One case uses only haptic sense, another case employs only visual sense, and the other case utilizes both senses. As a result, we can quantitatively confirm that the visual sense can differentiate angles more easily than the haptic sense.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131419972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869028
M. O. Silva, Gustavo M. Torres, Myke D. M. Valadão, E. V. C. U. Mattos, Antônio M. C. Pereira, Matheus S. Uchôa, Lucas M. Torres, N. ValneyM., Victor L. G. Cavalcante, José E. B. S. Linhares, Adriel V. Dos Santos, Agemilson P. Silva, Caio F. S. Cruz, Rômulo Fabrício, Ruan J. S. Belém, Lucas Fujita, Felipe A.A. Araújo, Carlos A. Monteiro, Thiago B. Bezerra, W. S. S. Júnior, Celso B. Carvalho
In this work, conducted by three partners, called UFAM/CETELI, Envision (TPV Group) and ICTS, we present an embedded system capable of recognizing actions and measuring the assembly time of human workers on an industrial production line. The system is composed of machine learning algorithms and the embedded platform NVIDIA Jetson Nano. In terms of performance, the system achieved rates (best case) 91%.
{"title":"Action and Assembly Time Measurement System of Industry Workers using Jetson Nano","authors":"M. O. Silva, Gustavo M. Torres, Myke D. M. Valadão, E. V. C. U. Mattos, Antônio M. C. Pereira, Matheus S. Uchôa, Lucas M. Torres, N. ValneyM., Victor L. G. Cavalcante, José E. B. S. Linhares, Adriel V. Dos Santos, Agemilson P. Silva, Caio F. S. Cruz, Rômulo Fabrício, Ruan J. S. Belém, Lucas Fujita, Felipe A.A. Araújo, Carlos A. Monteiro, Thiago B. Bezerra, W. S. S. Júnior, Celso B. Carvalho","doi":"10.1109/ICCE-Taiwan55306.2022.9869028","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869028","url":null,"abstract":"In this work, conducted by three partners, called UFAM/CETELI, Envision (TPV Group) and ICTS, we present an embedded system capable of recognizing actions and measuring the assembly time of human workers on an industrial production line. The system is composed of machine learning algorithms and the embedded platform NVIDIA Jetson Nano. In terms of performance, the system achieved rates (best case) 91%.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127583253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9868990
Jirayu Petchhan, S. Su
Nowadays, machine learning technology is growing exponentially, our research integrates AI and digital twin and/or transformation implemented in a wide range of industries. The issues can be seen in the fields which is the use of knowledge from both the virtual and physical world adapted all the way through. Part of obvious issue seems similar to deep transfer learning, such a domain shift occurrence during two domains. Hence, our proposed framework was developed to learn domain-invariant representation through Kernel Higher-order Tensor Matching (KHoM) and emphasized by cross-domain similarity learning via SoftTriple. Results, where are evaluated on public dataset and new fatal circumstance data, have been investigated that our framework is able to diminish discrepant domains from transferable on higher-level feature domain-invariant lightly on a less exemplary adaptations, but be obtained tremendously by the backing of the recognizability and realizing of object homogeneity through learning the likeness.
{"title":"Image Blending-assisted Few-Shot Cross-Domain Similarity Learning and Adaptation Tasks for Ambiguous Hazardous Incidents","authors":"Jirayu Petchhan, S. Su","doi":"10.1109/ICCE-Taiwan55306.2022.9868990","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9868990","url":null,"abstract":"Nowadays, machine learning technology is growing exponentially, our research integrates AI and digital twin and/or transformation implemented in a wide range of industries. The issues can be seen in the fields which is the use of knowledge from both the virtual and physical world adapted all the way through. Part of obvious issue seems similar to deep transfer learning, such a domain shift occurrence during two domains. Hence, our proposed framework was developed to learn domain-invariant representation through Kernel Higher-order Tensor Matching (KHoM) and emphasized by cross-domain similarity learning via SoftTriple. Results, where are evaluated on public dataset and new fatal circumstance data, have been investigated that our framework is able to diminish discrepant domains from transferable on higher-level feature domain-invariant lightly on a less exemplary adaptations, but be obtained tremendously by the backing of the recognizability and realizing of object homogeneity through learning the likeness.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127604538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869270
Hung-Chung Li, Meng-Che Tsai, Tsung-Xian Lee, Yi-Yung Chen, P. Sun
The visual impact of a head-mounted display (HMD) is much more complicated than the traditional display and will influence image quality performance. A psychophysical experiment is carried out to record the subject's threshold to perceive the stray light. Three kinds of virtual reality (VR) HMDs are compared, including Oculus Quest, Vive Focus Plus, and Vive Focus. The results show that Vive Focus Plus has a higher threshold meaning that the observer feels more challenging to detect the stray light. The stray light evaluation can become one of the critical indicators of image quality and apply to VR or augmented reality (AR) content design.
{"title":"Investigation of Stray Light Threshold for VR Head-Mounted Display","authors":"Hung-Chung Li, Meng-Che Tsai, Tsung-Xian Lee, Yi-Yung Chen, P. Sun","doi":"10.1109/ICCE-Taiwan55306.2022.9869270","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869270","url":null,"abstract":"The visual impact of a head-mounted display (HMD) is much more complicated than the traditional display and will influence image quality performance. A psychophysical experiment is carried out to record the subject's threshold to perceive the stray light. Three kinds of virtual reality (VR) HMDs are compared, including Oculus Quest, Vive Focus Plus, and Vive Focus. The results show that Vive Focus Plus has a higher threshold meaning that the observer feels more challenging to detect the stray light. The stray light evaluation can become one of the critical indicators of image quality and apply to VR or augmented reality (AR) content design.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114269796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869081
Yufeng Li, Lin Shang, Peng Pan
This paper studies the abnormal posture detection algorithm based on heuristic optimization. Using the data collected by sensors, the features such as acceleration and angular velocity are extracted and put into the classifiers for training. We select the appropriate heuristic algorithm according to different classifier models for optimization. The results demonstrate that, in binary classification experiment, the accuracy ratio of the K-Nearest Neighbor (KNN) model is 99.54%, and the AUC is 0.99. In quad classification experiment, The Support Vector Machine (SVM) model has a 94.32% accuracy ratio and a 0.95 AUC, which has the optimal performance.
{"title":"Heuristic Optimization based Abnormal Posture Detection Algorithm","authors":"Yufeng Li, Lin Shang, Peng Pan","doi":"10.1109/ICCE-Taiwan55306.2022.9869081","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869081","url":null,"abstract":"This paper studies the abnormal posture detection algorithm based on heuristic optimization. Using the data collected by sensors, the features such as acceleration and angular velocity are extracted and put into the classifiers for training. We select the appropriate heuristic algorithm according to different classifier models for optimization. The results demonstrate that, in binary classification experiment, the accuracy ratio of the K-Nearest Neighbor (KNN) model is 99.54%, and the AUC is 0.99. In quad classification experiment, The Support Vector Machine (SVM) model has a 94.32% accuracy ratio and a 0.95 AUC, which has the optimal performance.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114639628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-06DOI: 10.1109/ICCE-Taiwan55306.2022.9869211
Tsung-Han Tsai, Ping-Cheng Hao, Fong-Lin Tsai
In this paper, a customized speaker verification system combined with noise-cancellation using blind source separation was proposed. This system is divided into two phases: the noise-cancellation phase and the speaker verification phase. In the noise-cancellation phase, a fast time-frequency mask technique based on Short Time Fourier Transform (STFT) was proposed for separating a mixture of two input sounds in a single signal. After obtaining the separated speech data, this input is processed to the wake-up word system. In the speaker verification phase, we use Mel-Frequency Cepstral Coefficients (MFCC) as the feature extraction module. Then we train the feature data into a voiceprint model and a state sequence model of the speaker using Gaussian mixture model (GMM) and hidden Markov model (HMM), respectively. An analysis is done on noisy speech signals corrupted by white noise at different angles. Based on the output SIR (Signal to Interference Ratio) and SDR (Signal to Distortion Ratio) analysis, the improved accuracy is derived in the proposed system. We have obtained promising results in the real experimental environment.
{"title":"Customized Speaker Verification System with Noise-Cancellation using Blind Source Separation","authors":"Tsung-Han Tsai, Ping-Cheng Hao, Fong-Lin Tsai","doi":"10.1109/ICCE-Taiwan55306.2022.9869211","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869211","url":null,"abstract":"In this paper, a customized speaker verification system combined with noise-cancellation using blind source separation was proposed. This system is divided into two phases: the noise-cancellation phase and the speaker verification phase. In the noise-cancellation phase, a fast time-frequency mask technique based on Short Time Fourier Transform (STFT) was proposed for separating a mixture of two input sounds in a single signal. After obtaining the separated speech data, this input is processed to the wake-up word system. In the speaker verification phase, we use Mel-Frequency Cepstral Coefficients (MFCC) as the feature extraction module. Then we train the feature data into a voiceprint model and a state sequence model of the speaker using Gaussian mixture model (GMM) and hidden Markov model (HMM), respectively. An analysis is done on noisy speech signals corrupted by white noise at different angles. Based on the output SIR (Signal to Interference Ratio) and SDR (Signal to Distortion Ratio) analysis, the improved accuracy is derived in the proposed system. We have obtained promising results in the real experimental environment.","PeriodicalId":164671,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114768232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：