We propose a novel online multiple object tracker taking structure information into account. State-of-the-art multi-object tracking (MOT) approaches commonly focus on discriminative appearance features, while neglect in different levels structure information and the core of data association. Addressing this, we design a new tracker fully exploiting structure information and encoding such information into the cost function of the graph matching model. Firstly, a new measurement is proposed to compare the structure similarity of two graphs whose nodes are equal. With this measurement, we define a complete matching which performs association in high efficiency. Secondly, for incomplete matching scenarios, a structure keeper net (SKnet) is designed to adaptively establish the graph for matching. Finally, we conduct extensive experiments on benchmarks including MOT2015 and MOT17. The results demonstrate the competitiveness and practicability of our tracker.
Spinel zinc ferrites ZnFe2O4, prepared by co-precipitation method using the zinc nitrate Zn(NO3)2·6H2O and ferric nitrate Fe(NO3)3·2H2O as the raw materials, were characterized by the thermo gravimetric analysis (TG) and differential scanning calorimeter (DSC), X-ray diffraction (XRD) and scanning electron microscope (SEM). The influence of synthesis conditions, such as Zn/Fe molar ratio, pH value, the sintering temperature and time, on the microstructures was detailedly investigated. The relationships between the microstructures and the synthesis conditions were discussed. The results show that the pure spinel zinc ferrites ZnFe2O4 are formed when the Zn/Fe molar ratio is 1.05:2 at pH=8.5 or Zn/Fe molar ratio is 1:2 at Ph=9-10, and the precursors are sintered at 1100 °C for 4 h. Especially no other phases are observed when the Zn/Fe molar ratio is 1:2 at pH=10 and the precursor is sintered above 700 for 4 °C h. The higher sintering temperature and longer sintering time contribute to grain growth. 相似文献