机器视觉和应用程序发布机器视觉研究和开发方面的高质量技术贡献。具体来说，编辑鼓励在图像相关计算的所有应用和工程方面提交。特别是涉及机器视觉的科学、商业、工业、军事和生物医学应用的原创性贡献都在该期刊的范围内。特别强调图像处理和计算机视觉的工程和技术方面。以下方面机器视觉应用的兴趣：算法、架构、VLSI 实现、人工智能技术和机器视觉专家系统、前端传感、多维和多传感器机器视觉、实时技术、图像数据库、虚拟现实和可视化。论文必须包含重要的实验验证部分。

The journal "Machine Vision and Applications" publishes high-quality technical contributions in the field of machine vision research and development. Specifically, we encourage submissions related to all applications and engineering aspects of image-related computing. Original contributions involving scientific, commercial, industrial, military, and biomedical applications of machine vision are particularly welcome. The journal emphasizes the engineering and technical aspects of image processing and computer vision. We are especially interested in the following areas of machine vision applications: algorithms, architectures, VLSI implementations, artificial intelligence technologies and machine vision expert systems, front-end sensing, multi-dimensional and multi-sensor machine vision, real-time technologies, image databases, virtual reality, and visualization. All submitted papers must include significant experimental validation.

《Machine Vision and Applications》期刊致力于发布机器视觉领域的高质量技术研究和开发成果。我们鼓励提交与图像相关计算的各类应用和工程研究，尤其是涉及科学、商业、工业、军事和生物医学等领域的原创性贡献。期刊特别强调图像处理和计算机视觉的工程及技术方面。我们对以下机器视觉应用领域特别感兴趣：算法、架构、VLSI实现、人工智能技术和机器视觉专家系统、前端传感器、多维和多传感器机器视觉、实时技术、图像数据库、虚拟现实和可视化。所有提交的论文必须包含重要的实验验证部分。

Machine Vision and Applications

Gobinda Saha

Kaushik Roy

Online continual learning with saliency-guided experience replay using tiny episodic memory

使用微型情景记忆的显著性引导经验回放在线持续学习

Alessio Plebe

Giorgio Grasso

Localization of spherical fruits for robotic harvesting

球形水果的机器人采摘定位

Zeynep Nur Saracbasi

Cigdem Eroglu Erdem

Murat Taskiran

Nihan Kahraman

MYFED: a dataset of affective face videos for investigation of emotional facial dynamics as a soft biometric for person identification

MYFED：用于研究情感面部动态作为个人识别软生物特征的情感面部视频数据集

Abstract Existing Reject Option Classification formulations typically learn a function ( e.g. , softmax threshold) to select/reject uncertain classifier predictions. Such approaches leverage a user-defined cost of rejection or constraints on the accuracy or coverage of the selected predictions. We formulate a new objective for applications that have no such costs/constraints by using a natural constraint on the rejected predictions. Our proposed Reject Option Classification formulation eliminates regions of random chance classification in the decision space of any neural classifier and dataset. The goal is to maximize accuracy in the selected region while permitting a reasonable degree of prediction randomness in the rejected region. Optimally, the hope would be to reject more incorrect than correct predictions. We employ a novel selection/rejection function and learn per-class softmax thresholds using a validation set. Results demonstrate the advantages of our proposed method compared to naïvely thresholding calibrated/uncalibrated softmax scores. We evaluate 2-D points, imagery, and text classification datasets using state-of-the-art pretrained and learned models. Source code is available at https://github.com/osu-cvl/learning-idk .

Nicholas Kashani Motlagh

Jim Davis

Tim Anderson

Jeremy Gwinnup

Naturally constrained reject option classification

自然约束的拒绝选项分类

Abstract The object segmentation mask’s observation sequence shows the trend of changes in the object’s observable geometric form, and predicting them may assist in solving various difficulties in multi-object tracking and segmentation (MOTS). With this aim, we propose the entangled appearance and motion structures network (EAMSN), which can predict the object segmentation mask at the pixel level by integrating VAE and LSTM. Regardless of the surroundings, each EAMSN keeps complete knowledge about the sequence of probable changes in the seen map of the object and its related dynamics. It suggests that EAMSN understands the item meaningfully and is not reliant on instructive examples. As a result, we propose a novel MOTS algorithm. By employing different EAMSNs for each kind of item and training them offline, ambiguities in the segmentation mask discovered for that object may be recovered, and precise estimation of the real boundaries of the object at each step. We analyze our tracker using the KITTI MOTS and MOTS challenges datasets, which comprise car and pedestrian objects, to illustrate the usefulness of the suggested technique. As a result, we developed distinct EAMSNs for cars and pedestrians, trained using the MODELNET40 and Human3.6 M datasets, respectively. The discrepancy between training and testing data demonstrates that EAMSN is not dependent on training data. Finally, we compared our strategy to a variety of other ways. Compared to the published findings, our technique gets the best overall performance.

Ehsan Aryanfar

Mahdi Aliyari Shoorehdeli

Vahid Seydi

Entangled appearance and motion structures network for multi-object tracking and segmentation

多目标跟踪与分割的纠缠外观与运动结构网络

Abstract The success of visual-based localization requires the image features to be sufficiently captured in well-exposed images and reliably tracked among image sequences. In this paper, a learning-based exposure strategy algorithm is developed to improve the performance of visual odometry or simultaneous localization and mapping in scenes with sudden illumination changes and high dynamic range (HDR). The exposure value is predicted by optimizing a novel image information metric, which is calculated based on a multi-scale image histogram. Experimental observations show that the proposed metric is highly related to the localization performance, and achieves better localization accuracy when compared to other state-of-the-art metrics. Using this novel metric, the exposure control network is designed to predict the exposure value for the next image given a sequence of recently captured images as inputs. For different application scenarios, alternative network frameworks are proposed with the options to include an optimization module providing improved exposure values for feedback learning, but with additional computation complexity. The approach is light-weight for real-time video applications and the images captured using the predicted exposure values are well-exposed with better detected and matched features in a variety of challenging HDR scenes. Code will be available in https://github.com/leejieyu13/HDR-AE .

Jieyu Li

Ruiwen Zhen

Robert Stevenson

Automatic exposure strategy network for robust visual odometry in environments with high dynamic range

高动态范围环境下鲁棒视觉里程计的自动曝光策略网络

Abstract Semantic segmentation models need a large number of images to be effectively trained but manual annotation of such images has a high cost. Active domain adaptation addresses this problem by pretraining the model with a synthetically generated dataset and then fine-tuning it with a few selected label annotations (the “budget”) on real images to account for the domain shift. Previous works annotate a percentage of either individual pixels or whole target images. We argue that the first is infeasible in practice, and the second spends part of the budget on classes that the pretrained model may have already learned well. We propose a method based on the annotation of regions computed by Segment Anything, a recently introduced foundation model for class-agnostic image segmentation. The key idea is to assign a ground truth label to each of a tiny subset of regions, those for which the model is more uncertain. In order to increase the number of annotated regions we propagate the ground truth labels to most similar regions according to a hierarchical clustering algorithm that uses the features learned by the pretrained model. Our method outperforms the state-of-the-art on the GTA5 to Cityscapes benchmark by using fewer annotations, almost closing the gap between the synthetically pre-trained model and that obtained with full supervision of the real images. Furthermore, we present competitive results for budgets less than 1% of samples and also for a larger and more challenging target dataset, Mapillary Vistas.

Joan Serrat

Jose Luis Gómez

Antonio M. López

Closing the gap in domain adaptation for semantic segmentation: a time-aware method

领域自适应语义分割中的差距闭合：一种时间感知方法

Peng Guo

Shuguo Pan

Wang Gao

Kourosh Khoshelham

Self-supervised monocular depth estimation via joint attention and intelligent mask loss

通过联合注意力和智能掩码损失实现自监督单目深度估计

Yaobang Chen

Ping Zhao

A hybrid overlapping group sparsity denoising model with fractional-order total variation and non-convex regularizer

混合重叠组稀疏去噪模型与分数阶全变差及非凸正则化

Abbreviation	Machine Vis. Apps.
Journal Impact	2.60
Quartiles(Global)	ENGINEERING, ELECTRICAL & ELECTRONIC(Q2)

ISSN	0932-8092, 1432-1769
h-index	77

Publication Information	Publisher: Springer Verlag，Publishing cycle: Bimonthly，Journal Type: journal，Open Access Journals: No
Basic data	Year of publication: 1988，Proportion of original research papers: 100.00%，Self Citation Rate:8.30%， Gold OA Rate: 13.76%
Average review cycle	网友分享经验：平均6.5个月
Average recruitment ratio	网友分享经验：容易

Machine Vision and Applications

Journal Citation Format

A journal article with 1 author

A journal article with 2 authors

A journal article with 3 authors

A journal article with 5 or more authors

Books Citation Format

Thesis Citation Format

Web sites Citation Format

Patent Citation Format

Staying up late manually editing references? ivySCI automatically matches journals and helps you generate references with a single click.

Share Submission Experience

Online continual learning with saliency-guided experience replay using tiny episodic memory

Localization of spherical fruits for robotic harvesting

MYFED: a dataset of affective face videos for investigation of emotional facial dynamics as a soft biometric for person identification

Naturally constrained reject option classification

Entangled appearance and motion structures network for multi-object tracking and segmentation

Automatic exposure strategy network for robust visual odometry in environments with high dynamic range

Closing the gap in domain adaptation for semantic segmentation: a time-aware method

Self-supervised monocular depth estimation via joint attention and intelligent mask loss

A hybrid overlapping group sparsity denoising model with fractional-order total variation and non-convex regularizer

Entangled appearance and motion structures network for multi-object tracking and segmentation