目标鲁棒识别的抗旋转HDO局部特征描述

主方向直方图（Histograms of dominant orientations,HDO）是一种简单但性能优良的局部图像描述子,但是,原有的HDO特征描述不具备旋转不变性.本文提出一种抗旋转变换HDO特征描述方法,在进行RGT（Radial gradient transform）变换后,采用圆形邻域计算给定位置的结构张量,使得求取的主方向和一致性特征分量具备一定的旋转不变性,最后为增强辨别能力,采用了多扇区划分空间池化操作.在公开的MIT人脸数据集中的测试结果显示,如果图片不旋转,本文方法准确率与传统的HDO算法基本持平,达到92.10%,但当样本图片旋转后,本文算法准确率比传统HDO算法高10.36%.此外,在行人数据集、合成的旋转手掌和旋转人脸识别实验中,本文方法的检测结果也明显优于传统的HDO算法.另外本文方法在53Objects、ZuBuD和Kentuky三个数据集上的识别性能也优于大部分现有抗旋转算子.     

Learning Discriminative Space–Time Action Parts from Weakly Labelled Videos

Current state-of-the-art action classification methods aggregate space–time features globally, from the entire video clip under consideration. However, the features extracted may in part be due to irrelevant scene context, or movements shared amongst multiple action classes. This motivates learning with local discriminative parts, which can help localise which parts of the video are significant. Exploiting spatio-temporal structure in the video should also improve results, just as deformable part models have proven highly successful in object recognition. However, whereas objects have clear boundaries which means we can easily define a ground truth for initialisation, 3D space–time actions are inherently ambiguous and expensive to annotate in large datasets. Thus, it is desirable to adapt pictorial star models to action datasets without location annotation, and to features invariant to changes in pose such as bag-of-feature and Fisher vectors, rather than low-level HoG. Thus, we propose local deformable spatial bag-of-features in which local discriminative regions are split into a fixed grid of parts that are allowed to deform in both space and time at test-time. In our experimental evaluation we demonstrate that by using local space–time action parts in a weakly supervised setting, we are able to achieve state-of-the-art classification performance, whilst being able to localise actions even in the most challenging video datasets.     

采用旋转匹配的二进制局部描述子

针对二进制描述子主方向计算误差影响图像匹配正确性的问题,提出了一种旋转不变的二进制描述子构造和匹配方法。在以特征点为中心的同心圆周上等间隔选取采样点,按照旋转不变的模式选取采样点对进行灰度值比较,将比较结果连接成二进制串,作为区域的描述子。匹配时比较描述子在所有旋转模式中的汉明距离,取最小值作为描述子的距离,实现不依赖于主方向的旋转不变性。配合多尺度特征检测方法,将采样模式进行缩放,并对图像进行亚像素插值,实现尺度不变性。描述子匹配的实验结果表明,本文方法在旋转,尺度和光照变换下的匹配效果比当前依赖主方向的二进制描述子方法具有更高的鲁棒性。     

Psychophysical assessments of image-sensor fused imagery

The goal of this study was to determine the perceptual advantages of multiband sensor-fused (achromatic and chromatic) imagery over conventional single-band nighttime (image-intensified and infrared) imagery for a wide range of visual tasks, including detection, orientation, and scene recognition. Participants were 151 active-duty military observers whose reaction time and accuracy scores were recorded during a visual search task. Data indicate that sensor fusion did not improve performance relative to that obtained with single-band imagery on a target detection task but did facilitate object recognition, judgments of spatial orientation, and scene recognition. Observers' recognition and orientation judgments were improved by the emergent information within the image-fused imagery (i.e., combining dominant information from two or more sensors into a single displayed image). Actual or potential applications of this research include the deployment of image-sensor fused systems for automobile, aviation, and maritime displays to increase operators' visual processing during low-light conditions.     

Tracking in object action space

In this paper we focus on the joint problem of tracking humans and recognizing human action in scenarios such as a kitchen scenario or a scenario where a robot cooperates with a human, e.g., for a manufacturing task. In these scenarios, the human directly interacts with objects physically by using/manipulating them or by, e.g., pointing at them such as in “Give me that…”. To recognize these types of human actions is difficult because (a) they ought to be recognized independent of scene parameters such as viewing direction and (b) the actions are parametric, where the parameters are either object-dependent or as, e.g., in the case of a pointing direction convey important information. One common way to achieve recognition is by using 3D human body tracking followed by action recognition based on the captured tracking data. For the kind of scenarios considered here we would like to argue that 3D body tracking and action recognition should be seen as an intertwined problem that is primed by the objects on which the actions are applied. In this paper, we are looking at human body tracking and action recognition from a object-driven perspective. Instead of the space of human body poses we consider the space of the object affordances, i.e., the space of possible actions that are applied on a given object. This way, 3D body tracking reduces to action tracking in the object (and context) primed parameter space of the object affordances. This reduces the high-dimensional joint-space to a low-dimensional action space. In our approach, we use parametric hidden Markov models to represent parametric movements; particle filtering is used to track in the space of action parameters. We demonstrate its effectiveness on synthetic and on real image sequences using human-upper body single arm actions that involve objects.