ConvNet and LSH-Based Visual Localization Using Localized Sequence Matching

Automated Individual Cattle Identification Using Video Data: A Unified Deep Learning Architecture Approach

Individual cattle identification is a prerequisite and foundation for precision livestock farming. Existing methods for cattle identification require radio frequency or visual ear tags, all of which are prone to loss or damage. Here, we propose and implement a new unified deep learning approach to cattle identification using video analysis. The proposed deep learning framework is composed of a Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) with a self-attention mechanism. More specifically, the Inception-V3 CNN was used to extract features from a cattle video dataset taken in a feedlot with rear-view. Extracted features were then fed to a BiLSTM layer to capture spatio-temporal information. Then, self-attention was employed to provide a different focus on the features captured by BiLSTM for the final step of cattle identification. We used a total of 363 rear-view videos from 50 cattle at three different times with an interval of 1 month between data collection periods. The proposed method achieved 93.3% identification accuracy using a 30-frame video length, which outperformed current state-of-the-art methods (Inception-V3, MLP, SimpleRNN, LSTM, and BiLSTM). Furthermore, two different attention schemes, namely, additive and multiplicative attention mechanisms were compared. Our results show that the additive attention mechanism achieved 93.3% accuracy and 91.0% recall, greater than multiplicative attention mechanism with 90.7% accuracy and 87.0% recall. Video length also impacted accuracy, with video sequence length up to 30-frames enhancing identification performance. Overall, our approach can capture key spatio-temporal features to improve cattle identification accuracy, enabling automated cattle identification for precision livestock farming.

Weighted-Attribute Triplet Hashing for Large-Scale Similar Judicial Case Matching

Similar judicial case matching aims to enable an accurate selection of a judicial document that is most similar to the target document from multiple candidates. The core of similar judicial case matching is to calculate the similarity between two fact case documents. Owing to similar judicial case matching techniques, legal professionals can promptly find and judge similar cases in a candidate set. These techniques can also benefit the development of judicial systems. However, the document of judicial cases not only is long in length but also has a certain degree of structural complexity. Meanwhile, a variety of judicial cases are also increasing rapidly; thus, it is difficult to find the document most similar to the target document in a large corpus. In this study, we present a novel similar judicial case matching model, which obtains the weight of judicial feature attributes based on hash learning and realizes fast similar matching by using a binary code. The proposed model extracts the judicial feature attributes vector using the bidirectional encoder representations from transformers (BERT) model and subsequently obtains the weighted judicial feature attributes through learning the hash function. We further impose triplet constraints to ensure that the similarity of judicial case data is well preserved when projected into the Hamming space. Comprehensive experimental results on public datasets show that the proposed method is superior in the task of similar judicial case matching and is suitable for large-scale similar judicial case matching.

Vision Measurement of Gear Pitting Under Different Scenes by Deep Mask R-CNN

To accurately and quantitatively detect the gear pitting of different levels on the actual site, this paper studies a new vision measurement approach based on a tunable vision detection platform and the mask region-based convolutional neural network (Mask R-CNN). The shooting angle can be properly set according to the specification of the target gear. With the obtained sample set of 1500 gear pitting images, an optimized deep Mask R-CNN was designed for the quantitative measurement of gear pitting. The effective tooth surface and pitting was firstly and simultaneously recognized, then they were segmented to calculate the pitting area ratio. Considering three situations of multi-level pitting, multi-illumination, and multi-angle, several indexes were used to evaluate detection and segmentation results of deep Mask R-CNN. Experimental results show that the proposed method has higher measurement accuracy than the traditional method based on image processing, thus it has significant practical potential.

Large-Scale Place Recognition Based on Camera-LiDAR Fused Descriptor

In the field of autonomous driving, carriers are equipped with a variety of sensors, including cameras and LiDARs. However, the camera suffers from problems of illumination and occlusion, and the LiDAR encounters motion distortion, degenerate environment and limited ranging distance. Therefore, fusing the information from these two sensors deserves to be explored. In this paper, we propose a fusion network which robustly captures both the image and point cloud descriptors to solve the place recognition problem. Our contribution can be summarized as: (1) applying the trimmed strategy in the point cloud global feature aggregation to improve the recognition performance, (2) building a compact fusion framework which captures both the robust representation of the image and 3D point cloud, and (3) learning a proper metric to describe the similarity of our fused global feature. The experiments on KITTI and KAIST datasets show that the proposed fused descriptor is more robust and discriminative than the single sensor descriptor.

Image-Based Place Recognition Using Semantic Segmentation and Inpainting to Remove Dynamic Objects

Place recognition is an important step in intelligent driving, allowing the vehicle recognize where it is to plan its route. Obtaining distinguishable features can ensure the success of image-based place recognition. However, generating robust features across drastically appearance changing images is still a challenging problem. Deep features are frequently chosen instead of local features in the tasks of place recognition following the development of convolutional neural networks. But even the deep features generated by powerful neural models can cause unsatisfactory recognition results. This is perhaps due to a lack of information selecting process. The technology of semantic segmentation allows recognizing and classifying image information. Semantic segmentation followed by image inpainting provide a possibility of detecting, deleting and reconstructing annoying information.

This paper proves that dynamic information present in images such as vehicles and pedestrians damages the performance of place recognition and proposes a feature extraction system that includes a step to decrease the presence of dynamic information of an image. This system is composed of two stages: 1) dynamic objects detection and removing, 2) image inpainting to reconstruct the background of removed regions. Objects detection and removing consists of deleting unstable objects recognized by semantic segmentation method from images. Image inpainting and reconstructing deals with generating inpaint-images by repairing missing regions through image inpainting method. The robustness of the proposed approach is evaluated by comparing to the non-selecting deep feature based place recognition approaches over three datasets.