http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Monocular Camera Bird-Eye-View Generation using Lane Markers Prior
Muhammad Aasim Rafique,Muhamamd Ishfaq Hussain,Shikha Dubey,Khurbaev Sayfullokh,Moongu Jeon 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Retinotopy expresses the mapping of location preservation in the mechanism of human vision. However, a perception of the semantics of observed images in a scene is computed later in the hierarchy of neural information processing. Moreover, the utility of the perception to use it for planning is another challenging task as the human perception of objects in a scene is a putative orthographic projection. A monocular view from a front camera mounted on an autonomous vehicle captures a perspective projection view. Another challenge is in the use of a monocular camera in motion planning where navigation in the absence of any prior location information is required. This work suggests a solution of mapping the perspective view in a bird-eye-view (BEV) which is close to the orthographic projection. Furthermore, it suggests the use of the same processed information in an image to generate waypoints for maneuvering of the vehicle in absence of location information. The proposed technique uses clues inherent in the road infrastructure images using lane detection and utilizes a conventional computer vision’s inverse perspective mapping technique to generate BEV. The proposed technique is tested with the video dataset captured in urban and highway traffic to show its efficacy and its utility in motion planning.
Background subtraction using Gaussian-Bernoulli restricted Boltzmann machine
Sheri, Ahmad Muqeem,Rafique, Muhammad Aasim,Jeon, Moongu,Pedrycz, Witold Institution of Electrical Engineers 2018 IET image processing Vol.12 No.9
<P>The background subtraction is an important technique in computer vision which segments moving objects into video sequences by comparing each new frame with a learned background model. In this work, the authors propose a novel background subtraction method based on Gaussian-Bernoulli restricted Boltzmann machines (GRBMs). The GRBM is different from the ordinary restricted Boltzmann machine (RBM) by using real numbers as inputs, resulting in a constrained mixture of Gaussians, which is one of the most widely used techniques to solve the background subtraction problem. The GRBM makes it easy to learn the variance of pixel values and takes the advantage of the generative model paradigm of the RBM. They present a simple technique to reconstruct the learned background model from a given input frame and to extract the foreground from the background using the variance learned for each pixel. Furthermore, they demonstrate the effectiveness of the proposed technique with extensive experimentation and quantitative evaluation on several commonly used public data sets for background subtraction.</P>
3D Convolutional with Attention for Action Recognition
Labina Shrestha(러비나 스레스터),Shikha Dubey(시카 두베),Farrukh Olimov(파루크 올리모브),Muhammad Aasim Rafique(무하마드 아심 라피크),Moongu Jeon(전문구) 한국정보기술학회 2022 Proceedings of KIIT Conference Vol.2022 No.6
Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels and optical flow separately, models using a two-stream fusion technique, and models consisting of both convolutional neural network (CNN) and long-short term memory (LSTM) network are few examples of such complex models. Moreover, fine-tuning such complex models is computationally expensive as well. This paper proposes a deep neural network architecture for learning such dependencies consisting of a 3D convolutional layer, fully connected (FC) layers, and attention layer, which is simpler to implement and gives a competitive performance on the UCF-101 dataset. The proposed method first learns spatial and temporal features of actions through 3D-CNN, and then the attention mechanism helps the model to locate attention to essential features for recognition.