The large diameter and long focal length collimator can be used to measure the parallelism between the various optical axes of multi-axis photoelectric system. After moving, vibration or change of ambient temperature, the collimator components location will change, and its own parallelism will disorder. Outside the laboratory, it's difficult to recalibrate the disorder collimator. This will directly affect the reliability of the collimator measurement results. In this paper, a self-calibration method was proposed, the collimator structure was optimized, CCD detection imaging was introduced and self-calibration component was designed. The radial calibration and depth of focus calibration principles were studied in collimator. Based on this, a set of collimator will be developed, which can measure the optical axis parallelism and its own parallelism included. When the collimator own parallelism disorders in the use of an external field, it's easier to finish the self-calibration in the scene. The measurement accuracy of the instrument can be ensured. A set of sun fleck positioning system software will be programmed, and it can be used to coordinate with self-calibration and measuring the optical axis parallelism function in the collimator. The study in this paper has important practical significance for scientific research and engineering experiments.
Pedestrian detection belongs to a category of object detection is a key issue in the field of video surveillance and automatic driving. Although recent object detection methods, such as Fast/Faster RCNN, have achieved excellent performance, it is difficult to meet real-time requirements and limits the application in real scenarios. A coarse-to-fine deep neural network for fast pedestrian detection is proposed in this paper. Two-stage approach is presented to realize fine trade-off between accuracy and speed. In the coarse stage, we train a fast deep convolution neural network to generate most pedestrian candidates at the cost of a number of false positives. The detector can cover the majority of scales, sizes, and occlusions of pedestrians. After that, a classification network is introduced to refine the pedestrian candidates generated from the previous stage. Refining through classification network, most of false detections will be excluded easily and the final pedestrian predictions with bounding box and confidence score are produced. Competitive results have been achieved on INRIA dataset in terms of accuracy, especially the method can achieve real-time detection that is faster than the previous leading methods. The effectiveness of coarse-to-fine approach to detect pedestrians is verified, and the accuracy and stability are also improved.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.