Automatic Measurement of Morphological Traits of Typical Leaf Samples.

It is still a challenging task to automatically measure plants. A novel method for automatic plant measurement based on a hand-held three-dimensional (3D) laser scanner is proposed. The objective of this method is to automatically select typical leaf samples and estimate their morphological traits from different occluded live plants. The method mainly includes data acquisition and processing. Data acquisition is to obtain the high-precision 3D mesh model of the plant that is reconstructed in real-time during data scanning by a hand-held 3D laser scanner (ZGScan 717, made in Zhongguan Automation Technology, Wuhan, China). Data processing mainly includes typical leaf sample extraction and morphological trait estimation based on a multi-level region growing segmentation method using two leaf shape models. Four scale-related traits and six corresponding scale-invariant traits can be automatically estimated. Experiments on four groups of different canopy-occluded plants are conducted. Experiment results show that for plants with different canopy occlusions, 94.02% of typical leaf samples can be scanned well and 87.61% of typical leaf samples can be automatically extracted. The automatically estimated morphological traits are correlated with the manually measured values EF (the modeling efficiency) above 0.8919 for scale-related traits and EF above 0.7434 for scale-invariant traits). It takes an average of 196.37 seconds (186.08 seconds for data scanning, 5.95 seconds for 3D plant model output, and 4.36 seconds for data processing) for a plant measurement. The robustness and low time cost of the proposed method for different canopy-occluded plants show potential applications for real-time plant measurement and high-throughput plant phenotype.

R-YOLO: A Real-Time Text Detector for Natural Scenes with Arbitrary Rotation.

Accurate and efficient text detection in natural scenes is a fundamental yet challenging task in computer vision, especially when dealing with arbitrarily-oriented texts. Most contemporary text detection methods are designed to identify horizontal or approximately horizontal text, which cannot satisfy practical detection requirements for various real-world images such as image streams or videos. To address this lacuna, we propose a novel method called Rotational You Only Look Once (R-YOLO), a robust real-time convolutional neural network (CNN) model to detect arbitrarily-oriented texts in natural image scenes. First, a rotated anchor box with angle information is used as the text bounding box over various orientations. Second, features of various scales are extracted from the input image to determine the probability, confidence, and inclined bounding boxes of the text. Finally, Rotational Distance Intersection over Union Non-Maximum Suppression is used to eliminate redundancy and acquire detection results with the highest accuracy. Experiments on benchmark comparison are conducted upon four popular datasets, i.e., ICDAR2015, ICDAR2013, MSRA-TD500, and ICDAR2017-MLT. The results indicate that the proposed R-YOLO method significantly outperforms state-of-the-art methods in terms of detection efficiency while maintaining high accuracy; for example, the proposed R-YOLO method achieves an F-measure of 82.3% at 62.5 fps with 720 p resolution on the ICDAR2015 dataset.

Real-Time 3D Reconstruction of Thin Surface Based on Laser Line Scanner.

The truncated signed distance field (TSDF) has been applied as a fast, accurate, and flexible geometric fusion method in 3D reconstruction of industrial products based on a hand-held laser line scanner. However, this method has some problems for the surface reconstruction of thin products. The surface mesh will collapse to the interior of the model, resulting in some topological errors, such as overlap, intersections, or gaps. Meanwhile, the existing TSDF method ensures real-time performance through significant graphics processing unit (GPU) memory usage, which limits the scale of reconstruction scene. In this work, we propose three improvements to the existing TSDF methods, including: (i) a thin surface attribution judgment method in real-time processing that solves the problem of interference between the opposite sides of the thin surface; we distinguish measurements originating from different parts of a thin surface by the angle between the surface normal and the observation line of sight; (ii) a post-processing method to automatically detect and repair the topological errors in some areas where misjudgment of thin-surface attribution may occur; (iii) a framework that integrates the central processing unit (CPU) and GPU resources to implement our 3D reconstruction approach, which ensures real-time performance and reduces GPU memory usage. The proposed results show that this method can provide more accurate 3D reconstruction of a thin surface, which is similar to the state-of-the-art laser line scanners with 0.02 mm accuracy. In terms of performance, the algorithm can guarantee a frame rate of more than 60 frames per second (FPS) with the GPU memory footprint under 500 MB. In total, the proposed method can achieve a real-time and high-precision 3D reconstruction of a thin surface.

Real-Time Efficient Relocation Algorithm Based on Depth Map for Small-Range Textureless 3D Scanning.

As an important part of industrial 3D scanning, a relocation algorithm is used to restore the position and the pose of a 3D scanner or to perform closed-loop detection. The real time and the relocation correct ratio are prominent and difficult points in 3D scanning relocation research. By utilizing the depth map information captured by a binocular vision 3D scanner, we developed an efficient and real-time relocation algorithm to estimate the current position and pose of the sensor real-time and high-correct-rate relocation algorithm for small-range 3D texture less scanning. This algorithm mainly involves feature calculation, feature database construction and query, feature matching verification, and rigid transformation calculation; through the four parts, the initial position and pose of the sensors in the global coordinate system is obtained. In the experiments, the efficiency and the correct-rate of the proposed relocation algorithm were elaborately verified by offline and online experiments on four objects of different sizes, and a smooth and a rough surface. With more data frames and feature points, the relocation could be maintained real time within 200 ms, and a high correct rate of more than 90% could be realized. The experimental results showed that the proposed algorithm could achieve a real-time and high-correct-ratio relocation.

Registration of Aerial Optical Images with LiDAR Data Using the Closest Point Principle and Collinearity Equations.

Registration of large-scale optical images with airborne LiDAR data is the basis of the integration of photogrammetry and LiDAR. However, geometric misalignments still exist between some aerial optical images and airborne LiDAR point clouds. To eliminate such misalignments, we extended a method for registering close-range optical images with terrestrial LiDAR data to a variety of large-scale aerial optical images and airborne LiDAR data. The fundamental principle is to minimize the distances from the photogrammetric matching points to the terrestrial LiDAR data surface. Except for the satisfactory efficiency of about 79 s per 6732 × 8984 image, the experimental results also show that the unit weighted root mean square (RMS) of the image points is able to reach a sub-pixel level (0.45 to 0.62 pixel), and the actual horizontal and vertical accuracy can be greatly improved to a high level of 1/4⁻1/2 (0.17⁻0.27 m) and 1/8⁻1/4 (0.10⁻0.15 m) of the average LiDAR point distance respectively. Finally, the method is proved to be more accurate, feasible, efficient, and practical in variety of large-scale aerial optical image and LiDAR data.

Cross-scale cost aggregation integrating intrascale smoothness constraint with weighted least squares in stereo matching.

Cross-scale cost aggregation (CSCA) allows pixel-wise multiscale interaction in the aggregated cost computation. This kind of multiscale constraint strengthens the consistency of interscale cost volume and behaves well in a textureless region, compared with single-scale cost aggregation. However, the relationship between neighbors' cost is ignored. Based on the prior knowledge that costs should vary smoothly, except at object boundaries, the smoothness constraint on cost in a neighborhood system is integrated into the CSCA model with weighted least squares for reliable matching in this paper. Our improved algorithm not only has the advantage of CSCA in computational efficiency, but also performs better than CSCA, especially on the KITTI data sets. Experimental evidence demonstrates that the proposed algorithm outperforms CSCA in textureless and discontinuous regions. Quantitative evaluations demonstrate the effectiveness and efficiency of the proposed method for improving disparity estimation accuracy.

[Real-time automatic cloud detection during the process of taking aerial photographs].

The present paper adopted a method based on the spectrum signatures with thresholds to detect cloud. Through analyzing the characteristic in the aspect of spectrum signatures of cloud, two effective signatures were explored, one was brightness signature I and the other was normalized difference signature P. Combined with corresponding thresholds, each spectrum condition can detect some cloud pixels. By composing the union of two spectrum conditions together, cloud can be detected more completely. In addition, the threshold was also very important to the accuracy of the detection result. In order to detect cloud efficiently, correctly and automatically, this paper proposed a new strategy about the assignment of thresholds to acquire suitable thresholds. Firstly, the images should be classified into three kinds of types which were images with no cloud, with thin cloud and with thick cloud. Secondly, different assignment methods of automatic thresholds of signatures would be adopted according to different types of images. For images with thick cloud, they would be further classified into three kinds by another standard and assigned by different thresholds integrated by automatic thresholds from other spectrum signatures. The automatic thresholds were acquired by Otsu algorithm and an improved Otsu algorithm. For images with thin cloud, the cloud would be detected by score algorithm. Due to this flexible strategy, cloud in images can be detected rightly and if there isn't cloud in images the detection will be null to show that there is no cloud. Compared to the detection results of other different methods, the contrast results show that the efficiency of the detection method proposed in this paper is high and the accuracy satisfies the demand of real-time evaluation and the application range is wider.