Robust Powerline Equipment Inspection System Based on a Convolutional Neural Network.

Electric power line equipment such as insulators, cut-out-switches, and lightning-arresters play important roles in ensuring a safe and uninterrupted power supply. Unfortunately, their continuous exposure to rugged environmental conditions may cause physical or electrical defects in them which may lead to the failure to the electrical system. In this paper, we present an automatic real-time electrical equipment detection and defect analysis system. Unlike previous handcrafted feature-based approaches, the proposed system utilizes a Convolutional Neural Network (CNN)-based equipment detection framework, making it possible to detect 17 different types of powerline insulators in a highly cluttered environment. We also propose a novel rotation normalization and ellipse detection method that play vital roles in the defect analysis process. Finally, we present a novel defect analyzer that is capable of detecting gunshot defects occurring in electrical equipment. The proposed system uses two cameras; a low-resolution camera that detects insulators from long-shot images, and a high-resolution camera which captures close-shot images of the equipment at high-resolution that helps for effective defect analysis. We demonstrate the performances of the proposed real-time equipment detection with up to 93% recall with 92% precision, and defect analysis system with up to 98% accuracy, on a large evaluation dataset. Experimental results show that the proposed system achieves state-of-the-art performance in automatic powerline equipment inspection.

Keypoint-Based Disentangled Pose Network for Category-Level 6-D Object Pose Tracking.

Category-level 6-D object pose tracking is very challenging in the field of 3-D computer vision. Keypoint-based object pose estimation has demonstrated its effectiveness in dealing with it. However, current approaches first estimate the keypoints through a neural network and further compute the interframe pose change via least-squares optimization. They estimate rotation and translation in the same way, ignoring the differences between them. In this work, we propose a keypoint-based disentangled pose network, which disentangles the 6-D object pose change to 3-D rotation and 3-D translation. Specifically, the translation is directly estimated by the network and the rotation is indirectly calculated by singular value decomposition according to the keypoints. Extensive experiments on the NOCS-REAL275 dataset demonstrate the superiority of our method.

Jitter noise modeling and its removal using recursive least squares in shape from focus systems.

Three-dimensional shape recovery from the set of 2D images has many applications in computer vision and related fields. Passive techniques of 3D shape recovery utilize a single view point and one of these techniques is Shape from Focus or SFF. In SFF systems, a stack of images is taken with a single camera by manipulating its focus settings. During the image acquisition, the inter-frame distance or the sampling step size is predetermined and assumed constant. However, in a practical situation, this step size cannot remain constant due to mechanical vibrations of the translational stage, causing jitter. This jitter produces Jitter noise in the resulting focus curves. Jitter noise is invisible in every image, because all images in the stack are exposed to the same error in focus; thus, limiting the use of traditional noise removal techniques. This manuscript formulates a model of Jitter noise based on Quadratic function and the Taylor series. The proposed method, then, solves the jittering problem for SFF systems through recursive least squares (RLS) filtering. Different noise levels were considered during experiments performed on both real as well as simulated objects. A new metric measure is also proposed, referred to as depth distortion (DD), which calculates the number of pixels contributing to the RMSE in percentage. The proposed measure is used along with the RMSE and correlation, to compute and test the reconstructed shape quality. The results confirm the effectiveness of the proposed scheme.

Identification of Survival-Specific Genes in Clear Cell Renal Cell Carcinoma Using a Customized Next-Generation Sequencing Gene Panel.

PURPOSE: Although mutations are associated with carcinogenesis, little is known about survival-specific genes in clear cell renal cell carcinoma (ccRCC). We developed a customized next-generation sequencing (NGS) gene panel with 156 genes. The purpose of this study was to investigate whether the survival-specific genes we found were present in Korean ccRCC patients, and their association with clinicopathological findings. MATERIALS AND METHODS: DNA was extracted from the formalin-fixed, paraffin-embedded tissue of 22 ccRCC patients. NGS was performed using our survival-specific gene panel with an Illumina MiSeq. We analyzed NGS data and the correlations between mutations and clinicopathological findings and also compared them with data from the Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma (TCGA-KIRC) and Renal Cell Cancer-European Union (RECA-EU). RESULTS: We found a total of 100 mutations in 37 of the 156 genes (23.7%) in 22 ccRCC patients. Of the 37 mutated genes, 11 were identified as clinicopathologically significant. Six were novel survival-specific genes (ADAMTS10, CARD6, NLRP2, OBSCN, SECISBP2L, and USP40), and five were top-ranked mutated genes (AKAP9, ARID1A, BAP1, KDM5C, and SETD2). Only CARD6 was validated as an overall survival-specific gene in this Korean study (p = 0.04, r = -0.441), TCGA-KIRC cohort (p = 0.0003), RECA-EU (p = 0.0005). The 10 remaining gene mutations were associated with clinicopathological findings; disease-free survival, mortality, nuclear grade, sarcomatoid component, N-stage, sex, and tumor size. CONCLUSIONS: We discovered 11 survival-specific genes in ccRCC using data from TCGA-KIRC, RECA-EU, and Korean patients. We are the first to find a correlation between CARD6 and overall survival in ccRCC. The 11 genes, including CARD6, NLRP2, OBSCN, and USP40, could be useful diagnostic, prognostic, and therapeutic markers in ccRCC.

R Peak Detection Method Using Wavelet Transform and Modified Shannon Energy Envelope.

Rapid automatic detection of the fiducial points-namely, the P wave, QRS complex, and T wave-is necessary for early detection of cardiovascular diseases (CVDs). In this paper, we present an R peak detection method using the wavelet transform (WT) and a modified Shannon energy envelope (SEE) for rapid ECG analysis. The proposed WTSEE algorithm performs a wavelet transform to reduce the size and noise of ECG signals and creates SEE after first-order differentiation and amplitude normalization. Subsequently, the peak energy envelope (PEE) is extracted from the SEE. Then, R peaks are estimated from the PEE, and the estimated peaks are adjusted from the input ECG. Finally, the algorithm generates the final R features by validating R-R intervals and updating the extracted R peaks. The proposed R peak detection method was validated using 48 first-channel ECG records of the MIT-BIH arrhythmia database with a sensitivity of 99.93%, positive predictability of 99.91%, detection error rate of 0.16%, and accuracy of 99.84%. Considering the high detection accuracy and fast processing speed due to the wavelet transform applied before calculating SEE, the proposed method is highly effective for real-time applications in early detection of CVDs.

Age-invariant face recognition.

One of the challenges in automatic face recognition is to achieve temporal invariance. In other words, the goal is to come up with a representation and matching scheme that is robust to changes due to facial aging. Facial aging is a complex process that affects both the 3D shape of the face and its texture (e.g., wrinkles). These shape and texture changes degrade the performance of automatic face recognition systems. However, facial aging has not received substantial attention compared to other facial variations due to pose, lighting, and expression. We propose a 3D aging modeling technique and show how it can be used to compensate for the age variations to improve the face recognition performance. The aging modeling technique adapts view-invariant 3D face models to the given 2D face aging database. The proposed approach is evaluated on three different databases (i.g., FG-NET, MORPH, and BROWNS) using FaceVACS, a state-of-the-art commercial face recognition engine.