The weakly supervised Temporal Action Detection (TAD) by using the video-level annotations can lighten the burden of labor consumption. However, the current methods for weakly supervised TAD do not take full advantage of the short-term consistency between consecutive frames and the long-term continuity inside an action, resulting in less accurate detecting boundaries of actions in untrimmed videos. In this paper, the SuperFrame-based Temporal Proposal (SFTP) is proposed, in which superframes are formed for representing a series of consecutive frames with high temporal consistency and their features are pooled from the features of frames through the integration function. Then, the temporal proposal is built based on the multiple consecutive superframes and the features of all proposals are generated from a pyramidal feature hierarchy. This hierarchy consists of the designed Structured Outer-Inner Context (SOIC) features formed from superframe features and is able to explicitly characterize the temporal continuity inside a proposal. Furthermore, a novel Scale-Wise Normalization Strategy (SWNS) is proposed to identify proposals, which can effectively detect multiple actions with different duration in one untrimmed video. Extensive experiments are conducted on two public datasets: THUMOS14 and ActivityNet1.2 for performance evaluation. Our experimental results have demonstrated that the proposed approach is able to detect the boundaries of actions more effectively and obtain competitive mAP (mean average precision) compared with other approaches.

Person re-identification under one-shot setting is an under-researched semi-supervised task in essence, in which label estimation and data selection are two key modules. In this paper, we propose an effective strategy named Collaboration between the Labeled and Unlabeled(CLU) to estimate pseudo labels and select reliable data progressively. In CLU, label estimation is an iterative process where class center representations are estimated by high-scored unlabeled data and corrected by corresponding labeled data. Then reliable data are selected based on confidence scores decided by both labeled and unlabeled data actually. Moreover, a stepwise learning framework for one-shot video-based person re-identification named SCLU is implemented to validate the effectiveness of CLU. Extensive experiments conducted on MARS and DukeMTMC-VideoReID illustrate that CLU generates pseudo labels of high quality and facilitates the subsequent model training. Meanwhile, the developed scheme SCLU yields the state-of-the-art results on the two datasets.

In this paper, the ship target detection and recognition system of remote sensing imaging based on machine learning is designed according to the sparsity of interest targets in optical remote sensing image, and proposes a method of target detection and recognition based on morphological matching and machine learning. The slices of suspected targets are extracted quickly by visual enhancement technology that the amount of data processed is greatly reduced. The target information of interest is extracted in depth and the false alarm rate of detection is greatly reduced by using machine learning method to classify objects. In the system function and performance verification test, the real-time and accuracy index through 227 targets of 32 scenes GF-2 satellite images are tested what can detect and recognize about 20 objects per second. The recall rate of the system is more than 92%, and the efficiency of target detection method based on traditional morphological matching is less than 60% while the target recognition method base on machine learning improves the precision rate to over 97%.

A squint dual-antenna interferometric SAR (AT-InSAR) ocean current measurement method based on the traditional cross-track InSAR is studied in this paper. In the imaging geometry of cross-track InSAR, we can get an along-track baseline component in the presence of squint, which can be used for ocean current measurement. This additional working mode can extend the application efficiency of DEM acquisition InSAR satellites when flying over the ocean. The imaging geometry of dual-antenna squint interferometric SAR is established, and ocean current velocity measurement principle is given. Mainly, the ocean current velocity measurement performance of this novel working mode is analyzed.

The initialization is one of the less reliable pieces of Visual-Inertial SLAM (VI-SLAM) and Odometry (VI-O). The estimation of the initial state (camera poses, IMU states and landmark positions) from the first data readings lacks the accuracy and robustness of other parts of the pipeline, and most algorithms have high failure rates and/or initialization delays up to tens of seconds. Such initialization is critical for AR systems, as the failures and delays of the current approaches can ruin the user experience or mandate impractical guided calibration. In this paper we address the state initialization problem using a monocular-inertial sensor setup, the most common in AR platforms. Our contributions are 1) a general linear formulation to obtain an initialization seed, and 2) a non-linear optimization scheme, including gravity, to refine the seed. Our experimental results, in a public dataset, show that our approach improves the accuracy and robustness of current VI state initialization schemes.