SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation

Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self-supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB-2011 and Pascal VOC show that the proposed SAL-Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL-Net is embedded into a multiobject recognition and segmentation system, which realizes instance-aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.

Recognizing Zucchinis Intercropped with Sunflowers in UAV Visible Images Using an Improved Method Based on OCRNet

An improved semantic segmentation method based on object contextual representations network (OCRNet) is proposed to accurately identify zucchinis intercropped with sunflowers from unmanned aerial vehicle (UAV) visible images taken over Hetao Irrigation District, Inner Mongolia, China. The proposed method improves on the performance of OCRNet in two respects. First, based on the object region context extraction structure of the OCRNet, a branch that uses the channel attention module was added in parallel to rationally use channel feature maps with different weights and reduce the noise of invalid channel features. Secondly, Lovász-Softmax loss was introduced to improve the accuracy of the object region representation in the OCRNet and optimize the final segmentation result at the object level. We compared the proposed method with extant advanced semantic segmentation methods (PSPNet, DeepLabV3+, DNLNet, and OCRNet) in two test areas to test its effectiveness. The results showed that the proposed method achieved the best semantic segmentation effect in the two test areas. More specifically, our method performed better in processing image details, segmenting field edges, and identifying intercropping fields. The proposed method has significant advantages for crop classification and intercropping recognition based on UAV visible images, and these advantages are more substantive in object-level evaluation metrics (mIoU and intercropping IoU).

IMPROVEMENT OF THE METHODOLOGY OF EVALUATION OF TOURIST POTENTIAL OF THE REGION (ON THE EXAMPLE OF VINNITSA REGION)

A point assessment of the tourist potential of Vinnytsia region was conducted on the basis of an improved method of assessing the tourist potential of the region. It is proposed to assess the tourist potential of the administrative districts of the region according to four criteria: geographical location, natural tourist resources, historical and cultural tourist resources, infrastructure. Each of the criteria also contains a number of sub-criteria, the selection of which will differ depending on the specific object (region) of the study. After conducting a point assessment of the tourist potential of Vinnytsia region for each criterion, the relevant maps were drawn up, which reflect the geospatial differentiation of tourist resources in Vinnytsia region. Based on the analysis of the components of tourism potential of each administrative district of Vinnytsia region, its final score was made, including in terms of selected subregions, which allowed to identify patterns of geospatial organization of tourism potential of the region, its zoning and improve efficiency.

Robust Blocking of Human Faces with Personal Information Using Artificial Deep Neural Computing

High-speed wired and wireless Internet are one of the useful ways to acquire various types of media data easily. In this circumstance, people also can easily get media data including objects with exposed personal information through the Internet. Exposure of personal information emerges as a social issue. This paper proposes an effective blocking technique that makes it possible to robustly detect target objects with exposed personal information from various types of input images with the use of deep neural computing and to effectively block the detected objects’ regions. The proposed technique first utilizes the neural computing-based learning algorithm to robustly detect the target object including personal information from an image. It next generates a grid-type mosaic and lets the mosaic overlap the target object region detected in the previous step so as to effectively block the object region that includes personal information. Experimental results reveal that the proposed algorithm robustly detects the target object region with exposed personal information from a variety of input images and effectively blocks the detected region through grid-type mosaic processing. The object blocking technique proposed in this paper is expected to be applied to various application fields such as image security, sustainable anticipatory computing, object tracking, and target blocking.

Object-Independent Grasping in Heavy Clutter

When grasping objects in a cluttered environment, a key challenge is to find appropriate poses to grasp effectively. Accordingly, several grasping algorithms based on artificial neural networks have been developed recently. However, these methods require large amounts of data for learning and high computational costs. Therefore, we propose a depth difference image-based bin-picking (DBP) algorithm that does not use a neural network. DBP predicts the grasp pose from the object and its surroundings, which are obtained through depth filtering and clustering. The object region is estimated by the density-based spatial clustering of applications with noise (DBSCAN) algorithm, and a depth difference image (DDI) that represents the depth difference between adjacent areas is defined. To validate the performance of the DBP scheme, bin-picking experiments were conducted on 45 different objects, along with bin-picking experiments in heavy clutters. DBP exhibited success rates of 78.6% and 83.3%, respectively. In addition, DBP required a computational time of approximately 1.4 s for each attempt.

Object Detection Based on Region Decomposition and Assembly

Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks (CNNs) have been flourishing and provided the promising detection results. However, the detection accuracy is degraded often because of the low discriminability of object CNN features caused by occlusions and inaccurate region proposals. In this paper, we therefore propose a region decomposition and assembly detector (R-DAD) for more accurate object detection.In the proposed R-DAD, we first decompose an object region into multiple small regions. To capture an entire appearance and part details of the object jointly, we extract CNN features within the whole object region and decomposed regions. We then learn the semantic relations between the object and its parts by combining the multi-region features stage by stage with region assembly blocks, and use the combined and high-level semantic features for the object classification and localization. In addition, for more accurate region proposals, we propose a multi-scale proposal layer that can generate object proposals of various scales. We integrate the R-DAD into several feature extractors, and prove the distinct performance improvement on PASCAL07/12 and MSCOCO18 compared to the recent convolutional detectors.