The existing approaches for salient motion segmentation are unable to explicitly learn geometric cues and often give false detections on prominent static objects. We exploit multiview geometric constraints to avoid such mistakes. To handle nonrigid background like sea, we also propose a robust fusion mechanism between motion and appearance-based features. We find dense trajectories, covering every pixel in the video, and propose trajectory-based epipolar distances to distinguish between background and foreground regions. Trajectory epipolar distances are data-independent and can be readily computed given a few features' correspondences in the images. We show that by combining epipolar distances with optical flow, a powerful motion network can be learned. Enabling the network to leverage both of these information, we propose a simple mechanism, we call inputdropout. We outperform the previous motion network on DAVIS-2016 dataset by 5.2% in mean IoU score. By robustly fusing our motion network with an appearance network using the proposed input-dropout, we also outperform the previous methods on DAVIS-2016, 2017 and Segtrackv2 dataset.
ABSTRAKSebuah sistem monitoring tingkat kekeruhan air secara realtime dengan menggunakan sensor TSD-10 telah dirancang. Tingkat kekeruhan air diukur dengan memanfaatkan perubahan tegangan sensor akibat perubahan kekeruhan. Perancangan sistem monitoring ini terdiri dari perancangan perangkat keras dan perangkat lunak. Perangkat keras terdiri dari sistem sensor, driver motor dc menggunakan IC L293D, sistem minimum mikrokontroler ATmega8, dan modul USBtoSerial. Perancangan perangkat lunak menggunakan program BASCOM 2.0.75 untuk mikrokontroler dan Borland Delphi 7 untuk sistem GUI. Perangkat yang dirancang mampu melakukan pengukuran secara realtime dan menampilkan dalam bentuk angka serta menyimpan dalam bentuk database. Pengumpulan data dilakukan dengan membandingkan sistem yang dirancang dengan alat ukur kekeruhan standar HACH 2100N. Data yang diperoleh melalui pengukuran dianalisis menggunakan teori kesalahan dan interpolasi. Berdasarkan analisis yang dilakukan didapatkan tegangan keluaran sensor berkurang dengan kenaikan kekeruhan air dengan sensitivitas 2 mV/NTU. Derajat korelasi linier sensor didapatkan sebesar R 2 = 0,99 dan persentase ketepatan rata-rata pengukuran 93,49%.Kata kunci : Sistem Monitoring, Tingkat kekeruhan air, Sensor TSD-10 ABSTRACT A real time monitoring system for water turbidity levels using sensor TSD-10 has been designed. Water turbidity levels are measured through the utilization of voltage changes data in sensor triggered by turbidity alteration. The design of this monitoring system consists of hardware and software parts. The hardware comprises a sensor system, a dc motor driver using an IC L293D, a minimum system of microcontroller ATmega8 and USBtoSerial module. Meanwhile, the software uses BASCOM program 2.0.75 for microcontroller and Borland Delphi 7 in the GUI system. This designed device is able to perform real-time measurement, to display numeric form, and to store a database. Data collection is done by comparing the designed system with a standard turbidity measuring instrument named HACH 2100N. The data obtained through the measurement are analyzed using errors theories and interpolation. Based on the analysis, it is found that the output voltage of sensor decreases with the increase of turbidity with a sensitivity of 2 mV / NTU. The degree of sensor linearity correlation is determined in R 2 = 0.99. And, the percentage accuracy of average measurement is 93.49.
The design of hardware-friendly architectures with low computational overhead is desirable for low latency realization of CNN on resource-constrained embedded platforms. In this work, we propose CAxCNN, a Canonic Sign Digit (CSD) based approximation methodology for representing the filter weights of pre-trained CNNs.The proposed CSD representation allows the use of multipliers with reduced computational complexity. The technique can be applied on top of state-of-the-art CNN quantization schemes in a complementary manner. Our experimental results on a variety of CNNs, trained on MNIST, CIFAR-10 and ImageNet datasets, demonstrate that our methodology provides CNN designs with multiple levels of classification accuracy, without requiring any retraining, and while having a low area and computational overhead. Furthermore, when applied in conjunction with a state-of-art quantization scheme, CAxCNN allows the use of multipliers, which offer 77% logic area reduction, as compared to their accurate counterpart, while incurring a drop in Top-1 accuracy of just 5.63% for a VGG-16 network trained on ImageNet.
Local keypoint matching is an important step for computer vision based tasks. In recent years, Deep Convolutional Neural Network (CNN) based strategies have been employed to learn descriptor generation to enhance keypoint matching accuracy. Recent state-of-art works in this direction primarily rely upon a triplet based loss function (and its variations) utilizing three samples: an anchor, a positive and a negative. In this work we propose a novel ''Twin Negative Mining'' based sampling strategy coupled with a Quad loss function to train a deep neural network based pipeline (Twin-Net) for generating a robust descriptor that provides an increased discriminatory power to differentiate between patches that do not correspond to each other. Our sampling strategy and choice of loss function is aimed at placing an upper bound that descriptors of two patches representing same location could be at worst no more dissimilar than the descriptors of two similar looking patches that do-not belong to same 3D location. This results in an increase in the generalization capability of the network and outperforms its existing counterparts when trained over the same datasets. Twin-Net outputs a 128-dimensional descriptor and uses L 2 Distance as the similarity metric, and hence conforms to the classical descriptor matching pipelines such as that of SIFT. Our results on Brown and HPatches datasets demonstrate Twin-Net's consistently better performance as well as better discriminatory and generalization capability as compared to the state-of-art.INDEX TERMS Descriptor learning, twin negative sampling, patch matching, quad loss.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.