FEATURE EXTRACTION

فهرست عناوین اصلی در این پاورپوینت

فهرست عناوین اصلی در این پاورپوینت

● SLAM USING SINGLE LASER RANGE FINDER
● OUTLINE
● MOTIVATION
● MAIN CONTRIBUTIONS
● PROBABILISTIC FRAMEWORK
● OUTLINE
● FEATURE EXTRACTION
● OMITTING VARIANT FEATURES
● FEATURE EXTRACTION RESULTS
● OUTLINE
● RELIABILITY MEASURE CALCULATION
FOR INDIVIDUAL FEATURES
● MEASUREMENT NOISE
● QUANTIZATION ERROR
● FEATURE COVARIANCE
● OUTLINE
● MOTION PREDICTION
● OUTLINE
● DATA ASSOCIATION
● FILTERING AND ADDING NEW FEATURES
● OUTLINE
● RESULTS
● PURE LOCALIZATION
● RESULTS(PURE LOCALIZATION)
● PURE LOCALIZATION
● LSLAM
● LSLAM – SIMULATION
● LSLAM (REAL SCAN DATA)
● 8-CONCLUSION
● 9-REFERENCES

نوع زبان: انگلیسی حجم: 7.75 مگا بایت
نوع فایل: اسلاید پاورپوینت تعداد اسلایدها: 35 صفحه
سطح مطلب: نامشخص پسوند فایل: ppt
گروه موضوعی: زمان استخراج مطلب: 2019/06/15 11:58:15

لینک دانلود رایگان لینک دانلود کمکی

اسلایدهای پاورپوینت مرتبط در پایین صفحه

عبارات مهم استفاده شده در این مطلب

عبارات مهم استفاده شده در این مطلب

feature, ., robot, s, edge, state, laser, system, invariant, point, due, environment,

توجه: این مطلب در تاریخ 2019/06/15 11:58:15 به صورت خودکار از فضای وب آشکار توسط موتور جستجوی پاورپوینت جمع آوری شده است و در صورت اعلام عدم رضایت تهیه کننده ی آن، طبق قوانین سایت از روی وب گاه حذف خواهد شد. این مطلب از وب سایت زیر استخراج شده است و مسئولیت انتشار آن با منبع اصلی است.

http://saba.kntu.ac.ir/eecd/aras/students/Tamjidi/IFAC-Presentation11.ppt

در صورتی که محتوای فایل ارائه شده با عنوان مطلب سازگار نبود یا مطلب مذکور خلاف قوانین کشور بود لطفا در بخش دیدگاه (در پایین صفحه) به ما اطلاع دهید تا بعد از بررسی در کوتاه ترین زمان نسبت به حدف با اصلاح آن اقدام نماییم. جهت جستجوی پاورپوینت های بیشتر بر روی اینجا کلیک کنید.

عبارات پرتکرار و مهم در این اسلاید عبارتند از: feature, ., robot, s, edge, state, laser, system, invariant, point, due, environment,

مشاهده محتوای متنیِ این اسلاید ppt

مشاهده محتوای متنیِ این اسلاید ppt

slam using single laser range finder aliakbar aghamohammadi amir h. tamjidi hamid d. taghirad advance robotic and automation systems lab aras electrical and computer engineering department k. n. toosi university of technology iran outline ۱ motivation contributions ۲ probabilistic framework ۳ feature extraction ۴ error modeling for individual features ۵ motion prediction ۶ data association ۷ adding new features ۸ filtering iekf ۹ results ۱ conclusion ۱۱ refrences motivation traditional encoder base dynamic modeling are sensitive to slippage surface type changing imprecision in the parameters of robot s hardware. main contributions the key contributions of lslam include probabilistic framework state vector of the system comprises of robot pose and spatial features represented in world coordinates at system start up feature based map is initialized this map is updated dynamically by the extended kalman filter until operation ends. the probabilistic state estimates of the robot and features are updated during robot motion and feature observation. when new features are observed the map is enlarged with new states. mathematically the map is represented by a system s state vector and covariance matrix . here system is the indication of the collection of robots and environment. thus system s state vector is composed of the stacked state estimates of the robot and environment s features. p is the covarince matrix of the system which is a square matrix of equal dimension and can be partitioned into submatrix elements as follows the robot s state vector comprises of a metric ۲d position and its heading direction. feature states are ۲d position vectors of their locations. outline ۱ motivation contributions ۲ probabilistic framework ۳ feature extraction ۴ reliability measure calculation ۵ motion prediction ۶ data association ۷ adding new features ۸ filtering iekf ۹ results ۱ conclusion ۱۱ refrences feature extraction point features line features more informative features in methods which adopt a feature based approach for the map representation it is decisive to choose appropriate landmarks.. employing a range sensor however features such as walls or corners are used as landmarks in structured environments. moreover structured features are often invariant to height such as walls corners or columns. therefore a planar representation would be adequate for feature extraction. a concept that can be used to obtain salient features from the laser scan data is the local curvature value. features extracted from local curvature are viewpoint invariant measures and this means that they can be used as robust features in slam.. feature extraction steps features in our system features fall into two types jump edges are scan measurements associated to discontinuities in scanning process. ۲ high curvature points are defined as points in which curvature function shows high curve bending such as corners. these points are not associated to laser scan discontinuities. feature detection is composed of three main procedures scan data segmentation detection of high curvature points and discarding variant features. every segment dedicates two edge features start point and the end point features as an important prerequisite in exploiting features for localizing a mobile robot they have to be invariant with respect to robot s displacement. thus only invariant features are reliable for being selected omitting variant features there exist two kind of variant features those appear due to occlusion those appear due to low incidence angle two cases in which variation is observed in features i an edge of a segment which correlated to an obstacle partially occluded by another obstacle. such edges are established due to the occlusion not to the real landmark in the environment. ii when an edge of a segment established due to the sensors low range or lack of reflected laser beam occurs when incidence angle between laser ray and obstacle s surface is about or ۱۸ degrees. figure۳ lines in black represent the environment blue and red lines are the acquired scans from pose i and j respectively. upper feature is varying with respect to robot’s displacement but the other feature is an invariant one. figure۴ an edge feature established due to sensor low range is variant with respect to robot’s displacement. feature extraction results as an important prerequisite in exploiting features for localizing a mobile robot they have to be invariant with respect to robot s displacement. thus only invariant features are reliable for being selected. there are two cases in which variation is observed in features i an edge of a segment which correlated to an obstacle partially occluded by another obstacle. such edges are established due to the occlusion not to the real landmark in the environment. ii when an edge of a segment established due to the sensors low range or lack of reflected laser beam. this occurs when incidence angle between laser ray and obstacle s surface is about or ۱۸ degrees. for discarding variant features of case i we adopt proposed algorithm in our previous work and for avoiding those of case ii we discard obtained features with a distance from robot about laser range finder’s maximum measurable distance and obtained features with an incidence angle within the small neighborhood around or …

کلمات کلیدی پرکاربرد در این اسلاید پاورپوینت: feature, ., robot, s, edge, state, laser, system, invariant, point, due, environment,

این فایل پاورپوینت شامل 35 اسلاید و به زبان انگلیسی و حجم آن 7.75 مگا بایت است. نوع قالب فایل ppt بوده که با این لینک قابل دانلود است. این مطلب برگرفته از سایت زیر است و مسئولیت انتشار آن با منبع اصلی می باشد که در تاریخ 2019/06/15 11:58:15 استخراج شده است.

http://saba.kntu.ac.ir/eecd/aras/students/Tamjidi/IFAC-Presentation11.ppt

  • جهت آموزش های پاورپوینت بر روی اینجا کلیک کنید.
  • جهت دانلود رایگان قالب های حرفه ای پاورپوینت بر روی اینجا کلیک کنید.

رفتن به مشاهده اسلاید در بالای صفحه


پاسخی بگذارید

نشانی ایمیل شما منتشر نخواهد شد. بخش‌های موردنیاز علامت‌گذاری شده‌اند *