2018-10-30 星期二

標籤：its   filter   asc   HERE   png   ada   gen   fill   jpg   

English: listening、speaking、reading、writing、translation

1. Forget others‘ faults by remembering your own.

2. To like a person is not wrong, it is wrong to like a person who does not like you. ??? ????

3. Some people dream of success while others wake up and work hard at it.

4. The pillow is full of musty dreams filled with people who can‘t have it.

5. life has taught us that love does not consist in gazing at each other but in looking outward together in the same direction. 

6. AIDC   Auto Identification and Data Collection

paper

1. Rapid object detection using a boosted cascade of simple features (https://ieeexplore.ieee.org/abstract/document/990517)

Abstract:

This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.

2. Few-Example Object Detection with Model Communication (https://ieeexplore.ieee.org/document/8374906)

Abstract:

In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named "few-example object detection". The key challenge consists in generating trustworthy training samples as many as possible from the pool. Using few training examples as seeds, our method iterates between model training and high-confidence sample selection. In training, easy samples are generated first and, then the poorly initialized model undergoes improvement. As the model becomes more discriminative, challenging but reliable samples are selected. After that, another round of model improvement takes place. To further improve the precision and recall of the generated training samples, we embed multiple detection models in our framework, which has proven to outperform the single model baseline and the model ensemble method. Experiments on PASCAL VOC‘07, MS COCO‘14, and ILSVRC‘13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.

3. Object Detection and Image Classification with YOLO (https://www.kdnuggets.com/2018/09/object-detection-image-classification-yolo.html)

We explain object detection, how YOLO algorithm can help with image classification, and introduce the open source neural network framework Darknet.

 

There are a few different algorithms for object detection and they can be split into two groups:

1. 1. Algorithms based on classification – they work in two stages. In the first step, we’re selecting from the image interesting regions. Then we’re classifying those regions using convolutional neural networks. This solution could be very slow because we have to run prediction for every selected region. Most known example of this type of algorithms is the Region-based convolutional neural network (RCNN) and their cousins Fast-RCNN and Faster-RCNN.
   2. Algorithms based on regression – instead of selecting interesting parts of an image, we’re predicting classes and bounding boxes for the whole image in one run of the algorithm. Most known example of this type of algorithms is YOLO (You only look once) commonly used for real-time object detection.

 4. A gentle guide to deep learning object detection (https://www.pyimagesearch.com/2018/05/14/a-gentle-guide-to-deep-learning-object-detection/) (very good)

• The differences between image classification and object detection
• The components of a deep learning object detector including the differences between an object detection framework and the base model itself
• How to perform deep learning object detection with a pre-trained model
• How you can filter and ignore predicted classes from a deep learning model
• Common misconceptions and misunderstandings when adding or removing classes from a deep neural network
• Figure 1: The difference between classification (left) and object detection (right) is intuitive and straightforward. For image classification, the entire image is classified with a single label. In the case of object detection, our neural network localizes (potentially multiple) objects within the image.

 

 

turtlebot3 learning

1. turtlebot3 remote pc setup (http://emanual.robotis.com/docs/en/platform/turtlebot3/pc_setup/)(review because it is very important!!!)

supplement 

• Manual installation of ROS Kinetic

2. TurtleBot3Blockly Documentation (https://media.readthedocs.org/pdf/turtlebot-3-blockly-wiki/latest/turtlebot-3-blockly-wiki.pdf)

 

ubuntu relation setup

1. open-vm-tools (https://www.jianshu.com/p/687acbfd21a5)

 

2018-10-30 星期二