Pulse Compression Radar Ship Detection Method Based on Improved SSD

Author(s):  
Zhenjie Fu ◽  
Xianqiao Chen ◽  
Jinguang Xie ◽  
Yu Fan
2021 ◽  
Author(s):  
Tobias Schöffl ◽  
Richard Koschuch ◽  
Philipp Jocham ◽  
Johannes Hübl

<p>After a heavy rainfall event on August 31<sup>st</sup>, 2019, a debris flow at the Dawinbach in the municipality of Strengen (Tyrol, Austria) caused a blockage of the culvert below the provincial road B-316 and deposition in the residential area. The debris deposition raised up to 2 to 3 meters on the road and led to property damage to real estate. The total volume of the debris flow was approximately 15 000 cubic meters.</p><p>In order to control a further debris flow of this magnitude, the Austrian Service of Torrent and Avalanche Control started to construct mitigation measures. They include a channel relocation in order to significantly increase the channel crosssection. Hence the construction company STRABAG is also relocating the provincial road bridge.</p><p>Since the risk for this road section and for the workers on site is particularly high during the construction period, a combined monitoring and early warning concept was developed and implemented by the BOKU, Vienna and the company IBTP Koschuch.</p><p>The monitoring site consisting of a pulse compression radar and a pull rope system was installed 800m upstream from the fan. The combination of the two sensors now results in three major advantages.</p><ul><li>At sensor level, the system operates redundantly.</li> <li>A more reliable differentiation between increased discharge or debris flow is given.</li> <li>In the event of a false alarm, the system provides easier diagnosis and assignment of the fault.</li> </ul><p>Two events of increased runoff occurred during the deployment period. Both were successfully detected by the pulse compression radar. Here, the first event was used for threshold validation of the radar unit. Thus, an alarm could already be sent out automatically for the second one. The road is controlled by an integrated light signal system consisting of three traffic lights. A siren near the construction site can warn workers of an impending event by means of an acoustic signal. The reaction time after the alarm has been triggered is between 75 and 150 seconds, depending on the speed of the debris flow. The responsible authorities are informed by sending an SMS chain, which includes details about the type of process and the type of the activated triggering system.</p>


2020 ◽  
Vol 12 (1) ◽  
pp. 152 ◽  
Author(s):  
Ting Nie ◽  
Xiyu Han ◽  
Bin He ◽  
Xiansheng Li ◽  
Hongxing Liu ◽  
...  

Ship detection in panchromatic optical remote sensing images is faced with two major challenges, locating candidate regions from complex backgrounds quickly and describing ships effectively to reduce false alarms. Here, a practical method was proposed to solve these issues. Firstly, we constructed a novel visual saliency detection method based on a hyper-complex Fourier transform of a quaternion to locate regions of interest (ROIs), which can improve the accuracy of the subsequent discrimination process for panchromatic images, compared with the phase spectrum quaternary Fourier transform (PQFT) method. In addition, the Gaussian filtering of different scales was performed on the transformed result to synthesize the best saliency map. An adaptive method based on GrabCut was then used for binary segmentation to extract candidate positions. With respect to the discrimination stage, a rotation-invariant modified local binary pattern (LBP) description was achieved by combining shape, texture, and moment invariant features to describe the ship targets more powerfully. Finally, the false alarms were eliminated through SVM training. The experimental results on panchromatic optical remote sensing images demonstrated that the presented saliency model under various indicators is superior, and the proposed ship detection method is accurate and fast with high robustness, based on detailed comparisons to existing efforts.


Sign in / Sign up

Export Citation Format

Share Document