اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDirectional Cross Diamond Search Algorithm for Fast Block Motion Estimation
62
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In block-matching motion estimation (BMME), the search patterns have a significant impact on the algorithms performance, both the search speed and the search quality. The search pattern should be designed to fit the motion vector probability (MVP) distribution characteristics of the real-world sequences. In this paper, we build a directional model of MVP distribution to describe the directional-center-biased characteristic of the MVP distribution and the directional characteristics of the conditional MVP distribution more exactly based on the detailed statistical data of motion vectors of eighteen popular sequences. Three directional search patterns are firstly designed by utilizing the directional characteristics and they are the smallest search patterns among the popular ones. A new algorithm is proposed using the horizontal cross search pattern as the initial step and the horizontal/vertical diamond search pattern as the subsequent step for the fast BMME, which is called the directional cross diamond search (DCDS) algorithm. The DCDS algorithm can obtain the motion vector with fewer search points than CDS, DS or HEXBS while maintaining the similar or even better search quality. The gain on speedup of DCDS over CDS or DS can be up to 54.9%. The simulation results show that DCDS is efficient, effective and robust, and it can always give the faster search speed on different sequences than other fast block-matching algorithm in common use.
قيم البحث
اقرأ أيضاً
Current algorithmic approaches for piecewise affine motion estimation are based on alternating motion segmentation and estimation. We propose a new method to estimate piecewise affine motion fields directly without intermediate segmentation. To this
end, we reformulate the problem by imposing piecewise constancy of the parameter field, and derive a specific proximal splitting optimization scheme. A key component of our framework is an efficient one-dimensional piecewise-affine estimator for vector-valued signals. The first advantage of our approach over segmentation-based methods is its absence of initialization. The second advantage is its lower computational cost which is independent of the complexity of the motion field. In addition to these features, we demonstrate competitive accuracy with other piecewise-parametric methods on standard evaluation benchmarks. Our new regularization scheme also outperforms the more standard use of total variation and total generalized variation.
In this paper, we propose HOME, a framework tackling the motion forecasting problem with an image output representing the probability distribution of the agents future location. This method allows for a simple architecture with classic convolution ne
tworks coupled with attention mechanism for agent interactions, and outputs an unconstrained 2D top-view representation of the agents possible future. Based on this output, we design two methods to sample a finite set of agents future locations. These methods allow us to control the optimization trade-off between miss rate and final displacement error for multiple modalities without having to retrain any part of the model. We apply our method to the Argoverse Motion Forecasting Benchmark and achieve 1st place on the online leaderboard.
Visual motion estimation is a computationally intensive, but important task for sighted animals. Replicating the robustness and efficiency of biological visual motion estimation in artificial systems would significantly enhance the capabilities of fu
ture robotic agents. 25 years ago, in this very journal, Carver Mead outlined his argument for replicating biological processing in silicon circuits. His vision served as the foundation for the field of neuromorphic engineering, which has experienced a rapid growth in interest over recent years as the ideas and technologies mature. Replicating biological visual sensing was one of the first tasks attempted in the neuromorphic field. In this paper we focus specifically on the task of visual motion estimation. We describe the task itself, present the progression of works from the early first attempts through to the modern day state-of-the-art, and provide an outlook for future directions in the field.
The expanding adoption of digital pathology has enabled the curation of large repositories of histology whole slide images (WSIs), which contain a wealth of information. Similar pathology image search offers the opportunity to comb through large hist
orical repositories of gigapixel WSIs to identify cases with similar morphological features and can be particularly useful for diagnosing rare diseases, identifying similar cases for predicting prognosis, treatment outcomes, and potential clinical trial success. A critical challenge in developing a WSI search and retrieval system is scalability, which is uniquely challenging given the need to search a growing number of slides that each can consist of billions of pixels and are several gigabytes in size. Such systems are typically slow and retrieval speed often scales with the size of the repository they search through, making their clinical adoption tedious and are not feasible for repositories that are constantly growing. Here we present Fast Image Search for Histopathology (FISH), a histology image search pipeline that is infinitely scalable and achieves constant search speed that is independent of the image database size while being interpretable and without requiring detailed annotations. FISH uses self-supervised deep learning to encode meaningful representations from WSIs and a Van Emde Boas tree for fast search, followed by an uncertainty-based ranking algorithm to retrieve similar WSIs. We evaluated FISH on multiple tasks and datasets with over 22,000 patient cases spanning 56 disease subtypes. We additionally demonstrate that FISH can be used to assist with the diagnosis of rare cancer types where sufficient cases may not be available to train traditional supervised deep models. FISH is available as an easy-to-use, open-source software package (https://github.com/mahmoodlab/FISH).
We present an approach to recover absolute 3D human poses from multi-view images by incorporating multi-view geometric priors in our model. It consists of two separate steps: (1) estimating the 2D poses in multi-view images and (2) recovering the 3D
poses from the multi-view 2D poses. First, we introduce a cross-view fusion scheme into CNN to jointly estimate 2D poses for multiple views. Consequently, the 2D pose estimation for each view already benefits from other views. Second, we present a recursive Pictorial Structure Model to recover the 3D pose from the multi-view 2D poses. It gradually improves the accuracy of 3D pose with affordable computational cost. We test our method on two public datasets H36M and Total Capture. The Mean Per Joint Position Errors on the two datasets are 26mm and 29mm, which outperforms the state-of-the-arts remarkably (26mm vs 52mm, 29mm vs 35mm). Our code is released at url{https://github.com/microsoft/multiview-human-pose-estimation-pytorch}.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
