Automatic freezing-tolerant rapeseed material recognition using UAV images and deep learning

Background Freezing injury is a devastating yet common damage that occurs to winter rapeseed during the overwintering period which directly reduces the yield and causes heavy economic loss. Thus, it is an important and urgent task for crop breeders to find the freezing-tolerant rapeseed materials in the process of breeding. Existing large-scale freezing-tolerant rapeseed material recognition methods mainly rely on the field investigation conducted by the agricultural experts using some professional equipments. These methods are time-consuming, inefficient and laborious. In addition, the accuracy of these traditional methods depends heavily on the knowledge and experience of the experts. Methods To solve these problems of existing methods, we propose a low-cost freezing-tolerant rapeseed material recognition approach using deep learning and unmanned aerial vehicle (UAV) images captured by a consumer UAV. We formulate the problem of freezing-tolerant material recognition as a binary classification problem, which can be solved well using deep learning. The proposed method can automatically and efficiently recognize the freezing-tolerant rapeseed materials from a large number of crop candidates. To train the deep learning network, we first manually construct the real dataset using the UAV images of rapeseed materials captured by the DJI Phantom 4 Pro V2.0. Then, five classic deep learning networks (AlexNet, VGGNet16, ResNet18, ResNet50 and GoogLeNet) are selected to perform the freezing-tolerant rapeseed material recognition. Result and conclusion The accuracy of the five deep learning networks used in our work is all over 92%. Especially, ResNet50 provides the best accuracy (93.33$$\%$$ % ) in this task. In addition, we also compare deep learning networks with traditional machine learning methods. The comparison results show that the deep learning-based methods significantly outperform the traditional machine learning-based methods in our task. The experimental results show that it is feasible to recognize the freezing-tolerant rapeseed using UAV images and deep learning.

Crystal or Jelly? Effect of Color on the Perception of Translucent Materials with Photographs of Real-world Objects

Translucent materials are ubiquitous in nature (e.g. teeth, food, wax), but our understanding of translucency perception is limited. Previous work in translucency perception has mainly used monochromatic rendered images as stimuli, which are restricted by their diversity and realism. Here, we measure translucency perception with photographs of real-world objects. Specifically, we use three behavior tasks: binary classification of 'translucent' versus 'opaque', semantic attribute rating of perceptual qualities (see-throughness, glossiness, softness, glow and density), and material categorization. Two different groups of observers finish the three tasks with color or grayscale images. We find that observers' agreements depend on the physical material properties of the objects such that translucent materials generate more inter-observer disagreements. Further, there are more disagreements among observers in the grayscale condition in comparison to that in color condition. We also discover that converting images to grayscale substantially affects the distributions of attribute ratings for some images. Furthermore, ratings of see-throughness, glossiness, and glow could predict individual observers' binary classification of images in both grayscale and color conditions. Lastly, converting images to grayscale alters the perceived material categories for some images such that observers tend to misjudge images of food as non-food and vice versa. Our result demonstrates color is informative about material property estimation and recognition. Meanwhile, our analysis shows mid-level semantic estimation of material attributes might be closely related to high-level material recognition. We also discuss individual differences in our results and highlight the importance of such consideration in material perception.

Automatic Freezing-Tolerant Rapeseed Material Recognition Using UAV Images and Deep Learning

Background: Freezing injury is a serious and common damage that occurs to winter rapeseed during the overwintering period. The freezing injury directly reduces the rapeseed yield and causes serious economic loss. Thus, it is an important and urgent task for crop breeders to find the freezing-tolerant rapeseed materials in the process of breeding. Existing large-scale freezing-tolerant rapeseed material recognition methods mainly rely on the field investigation conducted by the agricultural experts using some professional equipment. These methods are time-consuming, inefficient and laborious. In addition, the accuracy of these traditional methods depends heavily on the knowledge and experience of experts. Methods: To solve these problems of existing methods, we propose a low-cost freezing-tolerant rapeseed material recognition approach using deep learning technology and unmanned aerial vehicle (UAV) images captured by a consumer drone. We formulate the problem of freezing-tolerant material recognition as a binary classification problem, which can be solved well using deep learning technology. The proposed method can automatically and efficiently recognize the freezing-tolerant rapeseed materials from a large number of candidates. To train the deep learning network, we first manually construct the real dataset using the UAV images of rapeseed materials collected by the Phantom 4 Pro. Then, five classic deep learning networks (AlexNet, VGGNet16, ResNet18, ResNet50 and GoogLeNet) are selected to perform the freezing-tolerant rapeseed material recognition. Result and Conclusion: The accuracy of the five deep learning networks used in our work is all over 92%. Especially, ResNet50 provides the best accuracy (93.33%) in this task. In addition, we also compare deep learning networks with traditional machine learning methods. The comparison results show that the deep learning-based approach significantly outperforms the traditional machine learning-based methods in our task. The experimental results show that it is feasible to recognize the freezing-tolerant rapeseed using UAV images and deep learning.

Computer Vision System for Expressing Texture Using Sound-Symbolic Words

The major goals of texture research in computer vision are to understand, model, and process texture and ultimately simulate human visual information processing using computer technologies. The field of computer vision has witnessed remarkable advancements in material recognition using deep convolutional neural networks (DCNNs), which have enabled various computer vision applications, such as self-driving cars, facial and gesture recognition, and automatic number plate recognition. However, for computer vision to “express” texture like human beings is still difficult because texture description has no correct or incorrect answer and is ambiguous. In this paper, we develop a computer vision method using DCNN that expresses texture of materials. To achieve this goal, we focus on Japanese “sound-symbolic” words, which can describe differences in texture sensation at a fine resolution and are known to have strong and systematic sensory-sound associations. Because the phonemes of Japanese sound-symbolic words characterize categories of texture sensations, we develop a computer vision method to generate the phonemes and structure comprising sound-symbolic words that probabilistically correspond to the input images. It was confirmed that the sound-symbolic words output by our system had about 80% accuracy rate in our evaluation.

Scale Ambiguities in Material Recognition

Many natural materials have complex, multi-scale structures. Consequently, the apparent identity of a surface can vary with the assumed spatial scale of the scene: a plowed field seen from afar can resemble corduroy seen up close. We investigated this ‘material-scale ambiguity’ using 87 photographs of diverse materials (e.g., water, sand, stone, metal, wood). Across two experiments, separate groups of participants (N = 72 adults) provided judgements of the material depicted in each image, either with or without manipulations of apparent distance (by verbal instructions, or adding objects of familiar size). Our results demonstrate that these manipulations can cause identical images to appear to belong to completely different material categories, depending on the perceived scale. Under challenging conditions, therefore, the perception of materials is susceptible to simple manipulations of apparent distance, revealing a striking example of top-down effects in the interpretation of image features.

A Semi Smart Adaptive Approach for Trash Classification

Waste management and recycling play a crucial factor in world economy sustainability as they prevent the squander of useful materials which can lead in garbage landfill reduction and cost reduction respectively. Garbage sorting into different categories plays an important role in recycling and waste management; but unfortunately, most garbage sorting still depends on labor which has a reverse impact on mankind and world economy, so there are different approaches to replace human separation by intelligent machines. In this article, we propose a comprehensive approach, Semi Smart Trash Separator to classify garbage and trash using the following technique: precycling by assigning a barcode or QR code to each material, which will enable the separation process as per assigned code; Magnetic separator helps in collecting conductive metal, then the non-conductive materials are classified according to their hardness. This test is a unique idea used in trash classification. Finally, if there is ambiguity in waste material classification barcode or material properties, the classification will be done using neural network techniques depending on the shapes of trash. Mat lab software is modified to handle convolutional neural networks in the image recognition (AlexNet and GoogLeNet) to be used in the trash classification processes and to test their accuracy. The tests are performed using a trustable data set. The material recognition accuracy rate from the obtained results on AlexNet and GoogLeNet are 75% and 83% respectively.