Pub Date : 2015-08-27DOI: 10.1109/IVS.2015.7225832
K. Hamada, Zhencheng Hu, Mengyang Fan, Hui Chen
Parking Assistance System (PAS) provides useful help to beginners or less experienced drivers in complicated urban parking scenarios. In recent years, ultrasonic sensor based PAS and rear-view camera based PAS have been proposed from different car manufacturers. However, ultrasonic sensors detection distance is less than 3 meters and results cannot be used to extract further information like obstacle recognition. Rear-view camera based systems cannot provide assistance to the circumstances like parallel parking which need a wider view. In this paper, we proposed a surround view based parking lot detection algorithm. An efficient tracking algorithm was proposed to solve the tracking problem when detected parking slots were falling out of the surround view. Experimental results on simulation and real outdoor environment showed the effectiveness of the proposed algorithm.
{"title":"Surround view based parking lot detection and tracking","authors":"K. Hamada, Zhencheng Hu, Mengyang Fan, Hui Chen","doi":"10.1109/IVS.2015.7225832","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225832","url":null,"abstract":"Parking Assistance System (PAS) provides useful help to beginners or less experienced drivers in complicated urban parking scenarios. In recent years, ultrasonic sensor based PAS and rear-view camera based PAS have been proposed from different car manufacturers. However, ultrasonic sensors detection distance is less than 3 meters and results cannot be used to extract further information like obstacle recognition. Rear-view camera based systems cannot provide assistance to the circumstances like parallel parking which need a wider view. In this paper, we proposed a surround view based parking lot detection algorithm. An efficient tracking algorithm was proposed to solve the tracking problem when detected parking slots were falling out of the surround view. Experimental results on simulation and real outdoor environment showed the effectiveness of the proposed algorithm.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115135094","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225686
Wahyono, A. Filonenko, K. Jo
In the field of intelligent transportation systems (ITS), an electronic road sign (ERS) is an important device for giving a real-time traffic-related information. The ERSs generally display dynamic text information that each character consists of matrix of a light-emitting diodes lamp, named LED text. This paper addresses an LED text detection and recognition method, as an application of ITS for assisting the driver. Our method is divided into several main stages. First, the ERS is localized from the input image using color model on the RGB-color space. Second, LED text contained on the ERS are detected based on supporting points. supporting points representing as a center of LED segment on a binary map of the input image. Third, each character of LED text is recognized using local spatial pattern feature and random forest classifier. Last, the recognized characters are merged into text line. Experimental results verify that the proposed method is robust to detect and recognize the LED text.
{"title":"Automatic LED text recognition method on electronic road sign using local spatial pattern and random forest classifier","authors":"Wahyono, A. Filonenko, K. Jo","doi":"10.1109/IVS.2015.7225686","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225686","url":null,"abstract":"In the field of intelligent transportation systems (ITS), an electronic road sign (ERS) is an important device for giving a real-time traffic-related information. The ERSs generally display dynamic text information that each character consists of matrix of a light-emitting diodes lamp, named LED text. This paper addresses an LED text detection and recognition method, as an application of ITS for assisting the driver. Our method is divided into several main stages. First, the ERS is localized from the input image using color model on the RGB-color space. Second, LED text contained on the ERS are detected based on supporting points. supporting points representing as a center of LED segment on a binary map of the input image. Third, each character of LED text is recognized using local spatial pattern feature and random forest classifier. Last, the recognized characters are merged into text line. Experimental results verify that the proposed method is robust to detect and recognize the LED text.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117260770","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225706
J. Eggert, Florian Damerow, Stefan Klingelschmitt
The Intelligent Driver Model (IDM) is a microscopic, time continuous car following model for the simulation of freeway and urban traffic. Its popularity is grounded in its simplicity and its capacity to describe both single vehicle velocity profiles as well as collective traffic behavior. Nevertheless, it lacks a series of properties that would be desirable for more realistic agent models. In this paper, as an alternative and improvement to the IDM, we propose the Foresighted Driver Model (FDM), which assumes that a driver acts in a way that balances predictive risk (e.g. due to possible collisions along its route) with utility (e.g. the time required to travel, smoothness of ride, etc.). Based on a risk concept developed for full behavior planning, we introduce driver model equations from the assumption that a driver will mainly try to avoid risk maxima in time and space. We show how such a model can be used to simulate driving behavior similar to full behavior planning models and which generalizes and reaches beyond the IDM modeling scenarios.
{"title":"The Foresighted Driver Model","authors":"J. Eggert, Florian Damerow, Stefan Klingelschmitt","doi":"10.1109/IVS.2015.7225706","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225706","url":null,"abstract":"The Intelligent Driver Model (IDM) is a microscopic, time continuous car following model for the simulation of freeway and urban traffic. Its popularity is grounded in its simplicity and its capacity to describe both single vehicle velocity profiles as well as collective traffic behavior. Nevertheless, it lacks a series of properties that would be desirable for more realistic agent models. In this paper, as an alternative and improvement to the IDM, we propose the Foresighted Driver Model (FDM), which assumes that a driver acts in a way that balances predictive risk (e.g. due to possible collisions along its route) with utility (e.g. the time required to travel, smoothness of ride, etc.). Based on a risk concept developed for full behavior planning, we introduce driver model equations from the assumption that a driver will mainly try to avoid risk maxima in time and space. We show how such a model can be used to simulate driving behavior similar to full behavior planning models and which generalizes and reaches beyond the IDM modeling scenarios.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"33 37","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120811793","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225771
Carlos Flores, V. M. Montero, Joshué Pérez, D. González, F. Nashashibi
Power consumption and battery life are two of the key aspect when it comes to improve electric transportation systems autonomy. This paper describes the design, development and implementation of a speed profile generation based on the calculation of the optimal energy consumption for electric Cybercar vehicles for each of the stretches that are covering. The proposed system considers a commuter daily route that is already known. It divides the pre-defined route into segments according to the road slope and stretch length, generating the proper speed reference. The developed system was tested on an experimental electric platform at Inria's facilities, showing a significant improvement in terms of energy consumption for a pre-defined route.
{"title":"Optimal energy consumption algorithm based on speed reference generation for urban electric vehicles","authors":"Carlos Flores, V. M. Montero, Joshué Pérez, D. González, F. Nashashibi","doi":"10.1109/IVS.2015.7225771","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225771","url":null,"abstract":"Power consumption and battery life are two of the key aspect when it comes to improve electric transportation systems autonomy. This paper describes the design, development and implementation of a speed profile generation based on the calculation of the optimal energy consumption for electric Cybercar vehicles for each of the stretches that are covering. The proposed system considers a commuter daily route that is already known. It divides the pre-defined route into segments according to the road slope and stretch length, generating the proper speed reference. The developed system was tested on an experimental electric platform at Inria's facilities, showing a significant improvement in terms of energy consumption for a pre-defined route.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124721708","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225844
J. Stellet, Jan Schumacher, Wolfgang Branz, Johann Marius Zöllner
Active safety systems employ surround environment perception in order to detect critical driving situations. Assessing the threat level, e.g. the risk of an imminent collision, is usually based on criticality measures which are calculated from the sensor measurements. However, these metrics are subject to uncertainty. Probabilistic modelling of the uncertainty allows for more informed decision making and the derivation of sensor requirements. This work derives closed-form expressions for probability distributions of criticality measures under both state estimation and prediction uncertainty. The analysis is founded on uncertainty propagation in non-linear motion models. Finding the distribution of model-based criticality metrics is then performed using closed-form expressions for the collision probability and error propagation in implicit functions. All results are illustrated and verified in Monte-Carlo simulations.
{"title":"Uncertainty propagation in criticality measures for driver assistance","authors":"J. Stellet, Jan Schumacher, Wolfgang Branz, Johann Marius Zöllner","doi":"10.1109/IVS.2015.7225844","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225844","url":null,"abstract":"Active safety systems employ surround environment perception in order to detect critical driving situations. Assessing the threat level, e.g. the risk of an imminent collision, is usually based on criticality measures which are calculated from the sensor measurements. However, these metrics are subject to uncertainty. Probabilistic modelling of the uncertainty allows for more informed decision making and the derivation of sensor requirements. This work derives closed-form expressions for probability distributions of criticality measures under both state estimation and prediction uncertainty. The analysis is founded on uncertainty propagation in non-linear motion models. Finding the distribution of model-based criticality metrics is then performed using closed-form expressions for the collision probability and error propagation in implicit functions. All results are illustrated and verified in Monte-Carlo simulations.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"153 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125899799","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225804
A. Reschka, Gerrit Bagschik, Simon Ulbrich, Marcus Nolte, M. Maurer
In this paper, the ability and skill graphs are introduced for modeling vehicle guidance systems in the concept phase of the development process (abilities), for online monitoring of system operation (skills), and to support driving decisions (skill levels) of automated road vehicles and advanced driver assistance systems. Both graphs rely on a decomposition of the human driving task. An ability is the entirety of conditions which are necessary to provide a certain part of the driving task. The ability graph can be developed in parallel to the item definition according to the ISO 26262 standard in the concept phase of the development process and can be used for supporting further development steps. A skill is defined as an abstract representation of a part of the driving task including information about the skills current performance. The skill graph is used to monitor the current system performance during operation and skill levels are input to driving decisions. Abilities and skills cover all aspects of the driving task including environment and self perception, data processing, decision making, and behavior execution. During operation of the developed item, the skill graph is instantiated as a (distributed) software component to process online information for assessing current skill levels. Each skill uses one or more performance metrics, which represent its current performance capability in relation to the maximum (inherent) ability level. The resulting information could replace the monitoring of the system by a human driver and can be used as an input to driving decisions of the vehicle to support appropriate and safe decisions.
{"title":"Ability and skill graphs for system modeling, online monitoring, and decision support for vehicle guidance systems","authors":"A. Reschka, Gerrit Bagschik, Simon Ulbrich, Marcus Nolte, M. Maurer","doi":"10.1109/IVS.2015.7225804","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225804","url":null,"abstract":"In this paper, the ability and skill graphs are introduced for modeling vehicle guidance systems in the concept phase of the development process (abilities), for online monitoring of system operation (skills), and to support driving decisions (skill levels) of automated road vehicles and advanced driver assistance systems. Both graphs rely on a decomposition of the human driving task. An ability is the entirety of conditions which are necessary to provide a certain part of the driving task. The ability graph can be developed in parallel to the item definition according to the ISO 26262 standard in the concept phase of the development process and can be used for supporting further development steps. A skill is defined as an abstract representation of a part of the driving task including information about the skills current performance. The skill graph is used to monitor the current system performance during operation and skill levels are input to driving decisions. Abilities and skills cover all aspects of the driving task including environment and self perception, data processing, decision making, and behavior execution. During operation of the developed item, the skill graph is instantiated as a (distributed) software component to process online information for assessing current skill levels. Each skill uses one or more performance metrics, which represent its current performance capability in relation to the maximum (inherent) ability level. The resulting information could replace the monitoring of the system by a human driver and can be used as an input to driving decisions of the vehicle to support appropriate and safe decisions.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114934161","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225818
B. Jager, P. Neugebauer, R. Kriesten, N. Parspour, Christian Gutenkunst
The electrification of the automotive powertrain provides completely new control options regarding the distribution of individual wheel moments. The integration of up to four independently controlled electrical engines in a vehicle allows individual adjustment of driving and braking torques to the current driving situation. Thus, electrical engines create a new kind of dynamic vehicle control. Unlike the Electronic Stability Control (ESC), Torque-Vectoring influences the vehicle dynamics not only through braking forces but also by setting up positive driving torques allowing for a new way of dynamic driving. In this paper two different control algorithms are developed in order to calculate a desired yaw moment to influence vehicle dynamics. The Torque-Vectoring algorithm distributes the yaw moment among the four wheels. The evaluation of the vehicle dynamic simulation has shown that the best results regarding the control quality can be reached by using the Fuzzy control algorithm to optimize the driving stability in extreme driving situations.
{"title":"Torque-vectoring stability control of a four wheel drive electric vehicle","authors":"B. Jager, P. Neugebauer, R. Kriesten, N. Parspour, Christian Gutenkunst","doi":"10.1109/IVS.2015.7225818","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225818","url":null,"abstract":"The electrification of the automotive powertrain provides completely new control options regarding the distribution of individual wheel moments. The integration of up to four independently controlled electrical engines in a vehicle allows individual adjustment of driving and braking torques to the current driving situation. Thus, electrical engines create a new kind of dynamic vehicle control. Unlike the Electronic Stability Control (ESC), Torque-Vectoring influences the vehicle dynamics not only through braking forces but also by setting up positive driving torques allowing for a new way of dynamic driving. In this paper two different control algorithms are developed in order to calculate a desired yaw moment to influence vehicle dynamics. The Torque-Vectoring algorithm distributes the yaw moment among the four wheels. The evaluation of the vehicle dynamic simulation has shown that the best results regarding the control quality can be reached by using the Fuzzy control algorithm to optimize the driving stability in extreme driving situations.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115531305","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225655
Dong-Woo Koh, Hang-Bong Kang
Reckless driving is one of the leading causes of car accidents. In particular, reckless driving by senior drivers often results in serious consequences due to driver physical fragility. As the population in developed countries is aging, the number of elderly drivers is increasing rapidly. Thus, careless or reckless driving in the elderly has become an important research issue. To investigate driving behavior in the elderly, we used a smartphone because it is equipped with gyro sensors. We constructed driving tests for elderly people on two types of courses, and also performed the same test to young people for data comparison. We then analyzed the data through the classification of GMM(Gaussian Mixture Model) with Periodogram in the elderly group. Using our method, we can classify elderly people's driving style on a gradient from smooth to aggressive behavior. Our proposed method will be useful in building early warning systems for elderly drivers as part of Advanced Driver Assistance Systems(ADAS).
{"title":"Smartphone-based modeling and detection of aggressiveness reactions in senior drivers","authors":"Dong-Woo Koh, Hang-Bong Kang","doi":"10.1109/IVS.2015.7225655","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225655","url":null,"abstract":"Reckless driving is one of the leading causes of car accidents. In particular, reckless driving by senior drivers often results in serious consequences due to driver physical fragility. As the population in developed countries is aging, the number of elderly drivers is increasing rapidly. Thus, careless or reckless driving in the elderly has become an important research issue. To investigate driving behavior in the elderly, we used a smartphone because it is equipped with gyro sensors. We constructed driving tests for elderly people on two types of courses, and also performed the same test to young people for data comparison. We then analyzed the data through the classification of GMM(Gaussian Mixture Model) with Periodogram in the elderly group. Using our method, we can classify elderly people's driving style on a gradient from smooth to aggressive behavior. Our proposed method will be useful in building early warning systems for elderly drivers as part of Advanced Driver Assistance Systems(ADAS).","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129341013","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225775
A. Ourabah, B. Quost, A. Gayed, T. Denoeux
This paper presents a novel approach for predicting the energy consumption of a plug-in hybrid electric vehicle (PHEV). We propose to estimate energy consumption strategy from data via regression applied to trip recordings. Descriptors of the trip elements are obtained from both recordings and statistics provided by a GPS navigation system. Trips are then split into elementary units corresponding to an homogeneous driving context. For each trip element, the optimal energy consumption strategy is computed via (expensive) dynamic programming simulations. Here, data analysis is used so as to identify descriptors of this trip element that are relevant to predict the energy consumption. Then, a polynomial model is fit to the data so as to estimate, for each new trip element, the optimal energy consumption strategy from the expected driving condition, rather than using dynamic programming. Our approach distinguishes itself by the fact that road context, driver style, road slope and auxiliary electrical power are taken into account to estimate the energy consumption of a PHEV. The accuracy of the prediction process is evaluated over test data, and demonstrates the interest of our approach in predicting energy consumption.
{"title":"Estimating energy consumption of a PHEV using vehicle and on-board navigation data","authors":"A. Ourabah, B. Quost, A. Gayed, T. Denoeux","doi":"10.1109/IVS.2015.7225775","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225775","url":null,"abstract":"This paper presents a novel approach for predicting the energy consumption of a plug-in hybrid electric vehicle (PHEV). We propose to estimate energy consumption strategy from data via regression applied to trip recordings. Descriptors of the trip elements are obtained from both recordings and statistics provided by a GPS navigation system. Trips are then split into elementary units corresponding to an homogeneous driving context. For each trip element, the optimal energy consumption strategy is computed via (expensive) dynamic programming simulations. Here, data analysis is used so as to identify descriptors of this trip element that are relevant to predict the energy consumption. Then, a polynomial model is fit to the data so as to estimate, for each new trip element, the optimal energy consumption strategy from the expected driving condition, rather than using dynamic programming. Our approach distinguishes itself by the fact that road context, driver style, road slope and auxiliary electrical power are taken into account to estimate the energy consumption of a PHEV. The accuracy of the prediction process is evaluated over test data, and demonstrates the interest of our approach in predicting energy consumption.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116500449","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225711
Alejandro González, Gabriel Villalonga, Jiaolong Xu, David Vázquez, J. Amores, Antonio M. López
Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multi-modality and strong multi-view classifier) affect performance both individually and when integrated together. In the multi-modality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.
{"title":"Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection","authors":"Alejandro González, Gabriel Villalonga, Jiaolong Xu, David Vázquez, J. Amores, Antonio M. López","doi":"10.1109/IVS.2015.7225711","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225711","url":null,"abstract":"Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multi-modality and strong multi-view classifier) affect performance both individually and when integrated together. In the multi-modality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114695820","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：