Abstract—Augmented Reality (AR) has become increasingly popular in recent years and it has a widespread application prospect. Especially in 2016, Pokémon Go, a location-based augmented reality game, has brought a dramatic impact on the global market of mobile games which has become the milestone of AR technology. AR is a kind of comprehensive application and it allows users to experience digital game play in a real world environment. Although a mature AR product includes various technologies, such as location technique, 3D reconstruction, its core technology is object identification and tracking. In this report, I implement the basic functions of object identification and tracking, then rendering a 2D model overlaying the object in the preview, which achieves the basic effect of Pokémon Go.


Bag of visual words.

In this project, there are three key techniques to implement functions. Firstly, we transform images to SURF descriptors and train these descriptors to get bag of visual words model. Next, we use this model to get the vector representation of object image and justify the validity of homography matrix to identify the object. Finally, after identifying the object, we use optical flow method to track it and overlay 2D model on the frame buffer according to the position of object.

The bag-of-visual-words (BoW) model is a simple assumption used in natural language processing and information retrieval, and has been widely applied in the computer vision field. The procedure includes two parts: learning and recognition. As shown in Figure 1, in the learning procedure, (i) Select a large set of images as the training data. (ii) Extract the SURF descriptors points of all the images in the training set and obtain the SURF descriptor for each interest point extracted. (iii) Quantize these descriptors by K-means clustering algorithm to form a codebook. (iv) Obtain the result of clustering as the visual vocabulary. (v) Extract the interest points of the object image. (vi) Obtain SURF descriptor for each interest point. (vii) Match the feature descriptors with the vocabulary by KNN algorithm. (viii) Build the histogram of object image.

Figure 1

Tracking

When tracking object by multi-scale Lucas-Kanade algorithm, we can get the homography matrix from the previous frame to current frame. Thus if we know the initial position of four corners, which actually have been given when the object is identified, the position of four corners can always be inferred. This is shown in Figure 2.

aaarticlea/png;base64,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" alt="" name="图片 7" width="653" height="192" align="bottom" border="0" />

Figure 2


Implement steps:

cv::FeatureDetector

cv::DescriptorExtractor

cv::DescriptorMatcher

(1) Create FeatureDetector and DescriptorExtractor.

aaarticlea/png;base64,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" alt="" name="图片 298" width="446" height="43" align="bottom" border="0" />

(2) Calculate SURF descriptors for each image.

aaarticlea/png;base64,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" alt="" name="图片 299" width="387" height="182" align="bottom" border="0" />

(3) Clusters the descriptors using k-Means algorithm.

//! clusters the input data using k-Means algorithm
CV_EXPORTS_W double kmeans( InputArray data,
int K,
CV_OUTInputOutputArray bestLabels,
TermCriteria criteria,
int attempts,
int flags,
OutputArray centers=noArray()
);

(4) Create flannBasedMatcher which is based on KD-Tree.

aaarticlea/png;base64,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" alt="" name="图片 286" width="507" height="24" align="bottom" border="0" />

(5)
Add centroids to
flannBasedMatcher (train collection), and these centroids will be
the indexes of histogram.

descriptor_matcher->add(centroid);

(6)
Update and balance the KD-Tree.

descriptor_matcher->train();

(7)
Use BoW model to get the vector representation of object image by
KNN algorithm.

aaarticlea/png;base64,iVBORw0KGgoAAAANSUhEUgAAApMAAABzCAIAAABLrx4BAAAACXBIWXMAABYlAAAWKQHl52v8AAAmCklEQVR4nO2du47cONaA1cCmPYEH5WA7tA0YUqczDt2AgWk4WiesZPcJOtjEDyDpAZxs0P8L/JsUk9nIsIEBusIepy3BQNthbzAFO5h+gF7eJJEUbyqpqqSq8zlwl4pFHl4PeXhI/eXh4SECAAAAAGAi/GXXAgAAAAAA0AHQ3AAAAAAwJUBzAwAAAMCUAM0NAAAAAFMCNDcAAAAATAnQ3AAAAAAwJUBzAwAAAMCUAM0NAAAAAFMCNDcAAMAEKK6S02UZxYsHhHYtC7Bjumjucn6EMUIPi3jdABOE95Y9y9RBwFpj/Qlq0MpYC+pAul5wNgtclvT/ktTWYapuPM/nTUs97BlMuOYusisczdLU2ry8ATTUamCozbfILk/zlfpQjDJokS7CKw3jo3nZ7SfTRJQYqYWbiyzp/vu9KSixOtkYYyioQWTYdEF5GUNJ9mcruUhQHOd0zX3A+iqA/WhRXoI19wpjqkTt+sAbIABS6EeN1inLFXtYYNJYRYAC23998PAqiBEms/JVlsx2Lc/O4KuTOL0ossMthBCgoKZEclY8nO1aiF1C9DF/y4Zh1XdohGpufJWXEcrs62lvADPy6pCvp1f5/AoVZ+KZ0EPCOoRxGaM4wrtcJIyXgozDpApIUeUYF0V21mcSNWnYnC/OQBv5gIICgEkSqLmJyozil6nd/uANEEC8eCBa/DIvlzk+q2wdCULlnGqkmG3wzNBihtXZVmUiFkh2EmUDj0zTjpqkXt4UimJTIml9y0I0dkXzGoVZaXa4TcjWT3GGoriYkckNJlkIVd3eglqxemkZ4VmWRWmw8onI36hwFZRinl1rp4qXc8VGzGKKkO3JZSWIpUXRBUFBP0ZNo5IiMexrsmhD22SHVt0XZ1F7sumhSy7cXW/9FsVadYIeUMGySYVHmOdFiWfnI4xnfzew66m1GdmCWQiqbm9dWHtWh35hYYv9YgwEae7iKsOkju2KwBsglBlCszxfFcUqQmQNSRQ3UYVxNGcGc1zgOL5Bj0u6vCQBaIPTOlXEW1i30ZyrJelBuZxnidyg4+Lq6LRJpcwv54meBOaWAHyVFXGvLYM1YabyOI6r/bBBDeaiXrQ4WZbVFRsZHXKloJJIGhr0sYN0tstOW/LG6k7E6KPVI4k8r+XvkIou5Co/xUn3GQYRLG9G266R+NtkD4IKylnUysMe2fTj6Xq9WxRVGJjHv8I5xuLvMstWKBvXCOOG/KSpxlYM7Vysh6u6vXUxUM8CKCGamy/mFvZRwxsgnIQqhhUz4lWxoQRFV1SLU1P5BVn/aT9Rpo2scWCxRieTvrR+aFucFRlmnUqaIRZX2iYKNyqKAEoSDYib8eMY7WR2x0zlYvKUEN29zDsYzP0FlWRniI5rcpwl8xVM5LBKQfFJdPOTck77rVTOLLk8L7NAKwWpF83/jsVQ5lc4G6z/8+mItFwgw+5V9WVQi6KUy7xsWiZbM3VwCXa2yWAZ+hBY1OtnMzQXzq7Xu0XROFYlXZM9zsmKDTObWfoHbbfSELTzESZ4f9daULlamzyezo3HVd3+unD2rP5spV+MhwDNzWodndnLwRugC/GMmsXVRwjhDF+VeIZuqF6Xv0uyi0L+TBVJ2cV3gS1VNcNOcrbQNZ4UgCdR/FFEsRKK9PmHDgkPC5s8zVLExxe+RO5kMPdCPVqxbISn3oKtowSyYSo5y9ByXv+EeReihVTOiHwinV/yQHTC3anQQprFI3STksUEHz5mWZFmXDQ6pvQ5NNIsuUhhZsU60chjB+rmnBHYJtfGX1C+om5C9shmIPau17tFMWbpgrTYUvxN2nNC/jVD0IhGGA/2GOgf5OFZXZsofRnjZW25DMda3aF1MUDPAih+zW0coDsF6ASZAreekSYyny/p1Lhe7kkz4n5+his2RCWeFuQNsGO4qfxlvdxnpouBPcx5b6/iXGVZKadYJfxYfhDHTep0mND2nyrhiyIKMVTwdYmmZLiRZo0xyAYdfcjyS9ge11b/qpzdZnVhbXKTBBd1n2yGYS+H/i2KIhvJLAazaYwwjhhYryyljTxMT5eRX3TtMtbqDqmLgXoWwPBpbssA3SFAN3gLYCM+bfExHyPYFLJA7QVkawOpc3p/FP5Ao4eZyqNoeXq0lB+Xw3qYy0Z47se+2Du/Dwo3u3GHF74HvN1RZj/a5J6wHyNMnKYznK/y01zaCt/+ufBd96x9wqO5vQP0wCO42I9BSLOKV3sYGuwomuo6qF4IpUhqWpbx2Whnw9S4qC5XalGuYzC3r18bI3xU+bE7EXZCLgBbsUVrXhHToFtr+VQvGf7wumhyzLVHNvGpSQ+y0NduKejSJgc0NrTYWlGvmYuBWpSTPRlh+LgqMbS7dZe68PcsQY/bOzbZL8aBW3Mzo4prgPYG6EB9YEDajwmisdCSCbKpU/G9c7MfE9++XZ4mUdOUqf9I0tnhbmenwkwbaVHtpdLFYO4qKAr3U8vzq6hYxalnsoznbLFSG/Fo5GUfb1K+r4bnGEteMPwMz3DzdtqEIml/V1xcJbtMRv6CciFMl9X+n+GsTlib7CODj60UNaNPLnq3qFBGMsKsjdiE3qTTlr8ufD3L3y/CJfG0qMrTfsorfqfmppPuOHX5pvkCeNEMOGwyyDWf1co0oyef+ByWVxK9ec2ZCG8T8ukXacopdl9KxdQcp53no7s7FWbZSBOF08Vg7iwo/pkPQ3njDaei10W8qOcxydkiLckse36kVHiHuY7wedFjUPxiBqDVJrkmk/EXlAPh66eXg5xcSJvsJYOPLRV1v1z0b1FeRjHCaKv8KpXwgmK5aG9CD6nLg+rC3bO8/SKsHPwtalWf/ZvwDfAOzS3uIbfbHLwBOtL9tu3krLiJ1LP/Z0Vy2ap5Orey2bikG2DqBy/XmA7v7FQYn1Cj1lDFt6WZx1+wRO6ConTIZmtkSbKLh2TdqTRPfZHeKCdTB581U3/XUikBYxL+gnKAFhdp3d5YKZX0mgstfm+b7CVDgJCbLuom2rVz0b9F+RIY0QizPkKtrrTH3Q+mOxPx1IW/ZwX0ixC8LUrcTrGLnf7hsGvujV9UXh9SNGO9pLc502IMhuRvGyw75cY4PWJYotrVqTBruvZMuXAXVJWmbR3vXe70LiU6QGSeMJ6m5SGoBBzBAlLXqyYx/CSk+gJFteIW1V3U/QpZxpKLwK63fouSS1iOWU1l9yOMr5Z9MXDjsL7CttxLYSOouj114W2u7n4R3to9IUPGkLFj1dybuqgcmDJ886nvNbcAAGwP8eomFb67J5/bBKaEVXN7Z7I7vXgE2C7yDhO/uQIAgGnAD9maDlvDy2YmS/j7uQFg2t6YAHCQGHeg4dWu0wY0NxBAwA7Twb88GADGC5hI9wzQ3AAAAAAwJUBzAwAAAMCUAM0NAAAAAFMCNDcAAAAATAnQ3AAAAAAwJUBzAwAAAMCUAM19WIgXssGxbAAADpU9GAa7aG52kZbrYmpvAA321vpo4DfFjg7eSnbw9k+TLOJN3oO8JGfr1T2mkhw1oyso9S1PIxKsN6Mr6vHQdXzYHoMOgzsiXHOLN4Ol1mrwBtg+4j2sSusRg0i3N9yx+7o3+4LbftDX/rRejtO+Jkm8E3fSL8nZAmOo7jHIMAhifQMAY6HvMDiGvhmsuTf+6rBNIK7ar9/WLv4+YOCmM2C78PUN3LUJjIg9GAZDNfd0Xx2GYoQbqwjGZczfML2HTHnbBthT2OwZ3mwBAIMSqLnpK+Gc73b0BghMhl+LLwwRzM4Wkdk6KmqDmzJ59wagJAiVc/EaWqLCZ2gx0966LozqFZIZRNmfU162E+v7tUokrW9raS1CStnfzM6Qak5v6figkhza8qlVdxj0xUfuklSENM1mlACz9OaiMhR1qG4LbC8/QQ+oYFmjkSPMG4YiySia3PoFNRxYeROG1hJooy1ovqImp93F8GXTXheWMOv17g5CcjmqccCwlc4aiSaGM5vOkmSNtmwVLKuabnnxjg9DNDlHXXgbTL9hMLhvbqFVB2nu4irDJAOJNWZvgLBUEppbvTTL/PIoVz7OE6Ug7AFWRUEUN+kCcTRnBnNc4Di+QY9JMkWxihCtD63fRrxku+1h8KYvC72cZ4nc4uPi6ui0SaWdi6h6Y26Er7Ii3smmg7uo2wXVC0t1+yG9IldKMomkwQVr70Qine1S6RV6gFV+ipNhbRUka5hLuMI5xuLvMstWKBtNk9tsQWnikcjrhtUMUsZySFqqgjzMm9G2Y335shlQF8P0bgcD9CxvbfJQ5pKcITTLc7rdmSVNpthw1MFY4s/FAE3OXxf2bAbjHmF8bKNVR2Gam+1UxQu76N4AAWm43fSr56xqsVhABwdACYquqBanpvKLJNKblzKvVGKo3pHldEkoMswakyR8caX5i3GboTsXiJvx4xitqbbl8THS5nFEeP6uIKMvm4RNyDKnzdG6Qu1Gj1MZSknyeHBRZHzCW8612QDLRZ6XWbVe4eORlC4ZC66kvPurO0DEVUnn4I9zUj6YGVHSP6icVHLRzHbd5HoW1BAQgbUWxWQo8yucSa2iXJKc1sXFWm+4S7A/m5GrLpiYA/Vuh5C9e1ZQNh0lmWRniE4x634Ucb9rNnKGyuDLxQBNLqQu3A0mZBi0jzABfXMbrZoRoLlZlaAze5zeAD4C1XbEWxIpxj+KKE66BEAIZ/iqxDN0Q18yL8eeZBeF/JnH0EF65pqnCZ+cLXTt6xVyDG/iswrJDg6Qdj+EvbTnYUrZMJWcZWhJGz15kgj3Q7SQokXkE+kVkosipVn+kj6WFYP7BszSBZGwFH+ncZSQf1G9VNh9k9t4QZHAacb+YqOSyUbNPNeUFoXQTUrWK/oQJg+RqJOTSkA2fXUxXO/2CNmjZ4XWpqMkqZc1rvuRiLPDQSH/+DBAkwusix4NhuMYYXxso1Vz/JrbW4Ud61inXJ6eRi6rqXfeFzAxJEUzny/pSqieUkoLIN8y1M2K1dUAQvamt4eaR8hZ3H//3VvdXpLHcg+i294VdAdE238S0H0TbsmgYwdZCoh9gc349MlWE4sFZbdNbgwFxVc2WqQJtdau6p0shhqmy+w2JJuRpy423ruZkL16VmA23SWJ0pcxXlYG81WWUb+ljsY/Vy6GaHJhddGjwQjsI4yXLbRqgU9ze6twvTqWiF8uUDnPqS1laM8sWtMxLyw2ES5Qe9rU2jjpCp1c7z/yRKcXG6zuUAmYyYub8vj+wpZ98qfS5HZeUFvAVxebL+rBelZPkgTFy5ybhYuCGvsXHW5MGigXziZ3GCNtKB7N7a3C7nXcJs4uFiWZ9mJqudrU6ZFqi0KDHWZTPQOtm0zqpKmCTdDKcOPYNGETTzbnbdxJ1jwZP2h1CwMan5GxuW0U5qUp2gNzJ5ENdA3m6u7PCJrcsAXVA92EyFdmSTJMEv5seuti8717nZ6lBuhSmw64nxo1C0fMbynrMkfz5mKAJrebkVYZYWTs48NmW7XArbkxu2jGUYXeAIFQo/88n3f04huMxjxC5uCmMTSe0SNlmpdB9R3bIlqeJlHT/6nfRNLZZW+Tp8J6wg0+OLsq0FnS2xt2qOoWHiu1AY1WU+n00qT1G0m7UOI2JW3F4KrugdhtkxuqoHrA9/YwmcFJLkv8+Nxghe7PJsNVF8P1blvi3p7FNVa9H6w7YAdn0ysJ81PL86uoWMVpt6j8uRigyW28Ltrg+WXeNtHb++aArboqQ4uhy6m56dwhTl2+ab4AHUCLizS5zDseqHBhta6w/Rg+d+N1QDpDa/tFgXce2XlbmqeL7ZlyeXq0rH8Rp53nhZs8Fdby8+QZCT2mTDJ5lsZlLucxjjv6VanxrV3demXFi3qik5wt0pLM01Ufe+2i7FV+mqtfs/4m46zuvoyhyQ1VUH0QDkq6DIoTU0+82Qyoi6F6tz0Bb88S7mN6LmqCajMEoRrzaJZ2tTZ5czFEk+tdF2HDoGOEEXmx983BWvWqPk1q9jl3aG5xD7m9Cr0BOkI9CUtSsqbTb5siOStuIvVygLOCvhhDg0587Ec1yLcXyoZZ/HKNaWDvU2Ebpaod/on2t1mW9Nmt7V7dws9TetJSqEl28ZC0FiXtRKUoTFNad3X3YxxNbqCC6gVapDfK4mz4JDzZDKqLYXq3nXbPiuZHZSQ1azHNFTeD0DZf0ts8pHx4ajOUHkOQf3wYosltui5amKfsrr45UKsWh+yti3W75t7CReXN0ZEKdTfacLtslwDWy2nVdFvBkC6VKWl3nDLeXDQJr38qrD6naMEtfKCQ+hNrls34qjsAXzZ5IHcxBibaWTaGnEc5Bk+73U2TG6agPLirjI7m2Zq/DZbAmc2guhiid7vQftLWbboASbtknNnsVJIoW8+8FDA+DNDk7HXRfxgUsYTYKlxRDdKq3ZHYNfd0LyoHAAAAusJ30PtfYg1sAavm9q7/dn9tCAAAANATefeXXyIEjJ7w93MDAAAA+8v+ndffX0BzAwAAjIlhPAzGmtyImdB7u0FzAwAAAMCUAM0NAAAAAFMCNDcAAAAATAnQ3AAAAAAwJUBzAwAAAMCUAM0NAIdLkSWn9EalxcMw7woAAGAbgOYGxsKX69/eXN+fv37z7tmuRRk3XN0OoW2L6i035rcadAPPj+YY5gAAsAV2r7k/vP/17e3Ju3/+dL5rSTbKTrN59/Zfnz6oj1QFeX/5/79dflcf3n46fX8XRd1kPpDa7M841FyCUJzTNTdcwAEAU2L3mhvYCUTFfrh+/us/nj+ln/78+p09/HL37tmJCPDlbnfSAVsiyQrXaw0AABglB6e5yVoni2+Kod9/PTYM2XxU6+lqPf3989vrk/+8OObPzp+dfLj974fXJ2y5fPfx9vj8WfThdtuSeyAZw6jXSrV/DAAAADvForm/ff7bvz9/lcd6BrOFHl/8/dXFj+IJ35sUH579dPP6pBWXsMRynrx4JVSFMMZy7t7+6+5t1ArTJFp/0iyx1A78hYaPmlRaYlcId5woxuSv5HCy2YZk4dExzfv15w8vqoSe/vX89tPH25+Iwo6ICn908u7RnWpjV/KoCBmcTWtBSUilrdQCzVqGoxIfJem6k69+MbCiTRYPCB/R94THJBKEeWkrlu+qCgTSd8xKXj0nH47qQLEukRJJ61sthPF7B4ocbQ81FnMkZc+chJbPNkoAJRUhgKnY9IR40J1vLQDAeLBo7h9Pzh99vvx+9/Hb86fNuEnWYURhnPxSPVGVDRu+v90r6oSrRinI1+vfL5/KY7EbTVVETCv8+fXvWgzk4edGx3z//Ob9cUu5mkaKA8mmEZH3P79+owJ8IYo7Ovnl2ae3zGD+4cvdk2evzh/dv41YgB9tQkZRpy1tf0Edf7n+9U2Tyv3lvz89aZJgxl2axfz0CK+le/vHQPUL9+siM4B8Lny8IpxlBX9ZfVud0fS66Z1WHGU+z5AsbVxkR6el9P3pPBlYtZE4j3Llo5yEV2trswP2uZkw0RZKv5/PsYizyOYGtc3d5yK5gAHg4LFZy48vXpxcvr/78OX+4sdqSUTWYVF0/qKxuFJ9Ji1AmYb7/H+3zysvp/vL92yYlsJ8uf70kf9FHj77KXL6NH0hw/p3ZXHJAt9f/n53IWkssnD82izOmDdWY/VlWObyB5NNI8dPSDzf7+kO9yPx6PzpydtrosWZqfzvx9F3/SfyCpgJeSfW6AHZ9BRUFYbKUwVQkqghY/6D0L3leuuwfjGUZUmLOMmJ3sFsLZgWtOBLosZEsStVwBRY5b1Nk64f2uZXXIcp8y/yCCthWHJVACWJ4CJopHMHNCaBc2bXkTKqxUR1ctvckOc4qx6gxQLVupvnGS3aTZe6z5F0Y4RAbQMAx77P/eyv50Sl3d59qXQYc1kiyzLxPf/4TlIt569/+nj7qfFy+nb34btuW3764ieTgdfI/cfbe5qEtLo9f/3q67ffLjWNpdiW6cJR3p31qLMDyaaJJ4/IZOVeeURL4/PH6x8+PDr5lep1+bvji3+8kj9TNX/bxYstsKCkADyJL9+JkJpFnSiEG5rj+dqG8x4xxOmChMfi7xQRfU1+Xi8/ybK+UFLimiccflZLVetJtmhptCYAT6Ig6Q6r3axJsE0Ho56tYCtlqpulyJiilucXte7O0oLpbeNEpp5lAADAcXiocd1QW5KZDZmM7OLbe2ZlVXY0Bd+46ZWt59jgu65szOG5SZHDV4q1CZehhjl//eb8tfg7wHZ8INk08PX7fesZM5hf3z958apSqGwRLGQwnC7rQFhBBZcktXsnvZbea8YgL/4sC0HfQtYNX077ls9bOMnlSSKOY+t3BZu9KBv50jdNoaHFTUrmT3ke2fQ2AAAtXL7l5z8/v7z9LCzJ1IZ8fPFzB/305fufvcXrS7OwOrKqtQPJZgs+KTl+8ojr1ONzZjNny9w/z5/qXmPtLequDF1Qa1gZBo/BEWuPCNQl+yhhkwu73u4cFQAAXXCeCuNOTMyS/PXLXfTo+S+SJxFdFEY292bK00c/UNcng6mzjbq4lNEtxlzf/PAk1PmLLayQ0yx6INnUU/zMNteZI55sFac71obgH36naltxBVf8yWXM2exSUF7WszIMG4Ml3tb+r30FbjZvJ/RAQDm86XtI2HJb3tmvHckELBORvyWy3fA4XSA8z+dJtv/nNQFgCNznuY9/eXZ8eX338dvx11syap/I2ovukt4a3Zsr+Bby9W9/i5rhnnokPf1Jdpnmu62aNxZD2LHfvv/reeMdxtybdduyD49Z9ECy2VAfu2oc8cJ4+qhSumQJblLb9myGFpSfsS62ZZL6OB5JwaS2ueqT/bUa+JZyfppEjXzUQw0tRqPW+Oyidvc22BloBrHH4Z2XDXUbQAlK8WmuO9BzxMxng9UFABPDcxPL0xfPz68/ff39vx+ik3fqudunL36+uP3tkiy8bj/Jz6UbNE/evf7vh/d3X69/O72uvz++UHUFX4pFUjz1wk74gulJKP5iwUgW5dYQcBDZ/P75zb8+y0GJADwLVjv2o+Mn9Nt7ZlSnKpnevPbelbwjm4EF5aQ+qt7jPHffGDxwlWza4FXgqk/eCJYkEo5b6qmsOB3QNtDyA+dihJcKStMY57KEseqIl2QLqotbBdEYOapTYHw+IsIbdH21e2CZ5wDAAeK9Q425LN3eRc/a53yOL/7x5ol21lmjvvGjevCEKMIfW2GiyGJ3PXn3zx+eyMeIzbegBCLWpFnctkIeSDYrrLe4WHn64tWvkXodzc/3JMt6OFc2wwrKRZJlKO91A1r/GLwJFDeRev0IOzSmh6vOM5tjqSZg9Tq2UnCjgeRzUdby09zEWYK1EMwEZN4oqMweTbZqXa8ZzVmV9XD4A4D9w3/7qezD3PVbyo/P//PP5540qtPAJqjivLD+kui8k3ee2BXIEGP2U9vnbHp+TrTyzQvTF2qm2sHMWXZl01VQBjHaUdnqL5w+McjXfMtnldRzS63LwJH5cnD3aSf7leKGb7oenPKFD0pCf2IQ2JqOMXe2LHM7htOXHQAOioO7txwAgKkg75+PzuoAALsDNDcA7BPeo+RTvP97ijIDwAYBzQ0AwEiBl5ACgBHQ3ACwT8BVoQCw/4DmBgAAAIApAZobAAAAAKYEaG4AAAAAmBKguQEAAABgSoDmBgAAAIApAZobAAAAAKbEnmhucdcSXNgAHCJ4frTJq9iBfQHGyb3pLF00N7udaZSVXmDMrkikrwhGo5NuCvAuPcrKlWBSBrz0edp0rIvqNaK2pl/iHDcv4IxRiuD270kxXN8cdJwcrzpwQvOO8dF8coJr7MeaO0Eozulccs3mONFGqLEfudgppjWJuE60W8FurS7wnAhsfTnn6urycrnaXOpsVgCTAT/j6Jt9x8kpoLwq3tAx6tcgz/GkR8r90NxwSyIwCGXZWpNgPOL3S2Iy/jhexbEqSqK2Zy8vLs5mW5YMGCN7Pk627uyn748vW/Ml8TrZaevuPdHcwJ4wgk0osiDBjeomf8Xkr1Gq7yLLXHqbaO4VUdzxGaht4CCgtoQirpfZXJGbtgbEK9+zrEBT3XjzaG7F9OANYLIG+YwX7iC07Av6JGrCKCHUWVZLgHpjFGHT75Vfkw9H9Q81SZ3JeIV0wkRMFg8IsyRiSVglHa0qpO+CcxFSG4UzD87q7lcOPHqiikp8lIT+qsq6EMVT3QEBWL6I6p6L7s4U9yLWFPco6iLC1PAZp2jtoUexpRts3pqtXQqh7J2TD3kdqF7g8x8rsbJfSRYA+nlFP0ZNQi0DgU9INcCw9oVJ9U0n/cZJSz7b2McH056TCN01Lw5I9Ej+tEAk1aIoolYnQWkak3ab48y4TODi7nx7w4FDc3urqWWcIJ+TluKVA5T56TxRCqOVSJnPM6RVJIkmx1IIPRIf9PdNGuT3SdShrbTLoZXP3kKSuMRISEazufAjiZo5oVGGjk4W/qKOi+zoVCkoJQ/e6q6erl0OzJhHk8lPj7C3PwvXLL17UQtZrnzUJLAHoH08StjUnatuprhvUFLy79Bo6iISZvwYtRW3pnBlxaqpTUUCnF/Kaq+9RU5/sYEt7QLny0aQ1fISPzbPEAxCtgKoPx9Gvin0zSFwd5ye6oD2Uvp9Y6IusvmwarsbfM/f4qsntsjGvCi3a242o1cKVqsZtsfWml/KsxiWf3lgJVFJTaOqPCUMeaQZJstcrmCWSFPe9ZuRHK8lZpuXVRK8AWJM/k/qXzv8R4SI+kK91GZrTiH9EBHpj5Oc/Y7KlRZUTiq5KP22qaFKICAXYUWtFJSeB391D1AOEZfwQWjv9haVlB/n+RZbLsICUNWdUS3OFHcS6QPWruuC/YLKZ1LcQZRMA+mr6OVVeSZpPWUBywKUBandmP0wrR/28lBbLcn0oE5ISSRASBpUWYiT+cbVuqJYmEDf9BMyTlYBzd2/vzoQS2Cuu3me0WKjats6uaVw1W1ckLMBgPx27e61BWyam9ktnQUr1LLUFEXNaA1KnreQNdVCToT1TLU9J9miXY5SCLTGpqPc3sQOh1DdXioRpXJAi5uU9NzWaN9LSL5bicXfKSJjAkmw1hgJ0yNSYl0TCCxqKQBPom7YodXtLIf2vN0y5a4dQM2G80C13c5FcACE5hnOSq64Vc29+7pg8KHc1IZnZxfpGQ9jU6xC40nP6QcSuFKaLJYL+SdxEkelc821JrJ8SiIBQvJwV1erWMwwiNSDmzdH3zcHw5rEQOqg1t1ZWrD+u1FbtMd9M0po58HSBExi/O/Kde5zx7F9Ks2m/OrOjfQNEhYSVlHCCNMeZ/ng4503Il0zdC3TRBnfXLlqYRSRxVeqHaefkPLkzjLR802W3YQVtT1ASHUboujRAajlPDEtvcv89DRyndLqkU05yHzOjltVWZPXWLuti/6s/qBmcGV/WvomVpbZGxNCQJW19Eks5gOFFKp8eZkvo02dVR993xwMTxJ91QFLgi97aJ1uVm9XG9V7e/WDTXOz1tS/F/CRW/j4sWqVLULqXBWw4t9j8kUwjqLucijF6r5CZtEIz3O8gUMdtNXHfPBna47CMFDvS1142PRJ8KHgqp7PMbiW3/Lx8oNoDwOpgzqqDTN+/7L+2DQ3m1+ViiVBPdjK17Fh7gVi5cXauGQ8Ny1dN4+wTbXNjHZBdIsw72tJiLV9ENp7TPZZvjkXvYu6S3UPgPv2kzgrFiW1uiXZ5gSymAtGUBcc1kPXjGX2mK5YXW7Y5RVV2+2NblNYZZ3ugFm/hxSyQSzV2XRDNp5vntG0h40ymDqoLNh07r2Z7ht+wSv3FOligR0TNs3Nm1OtZg0TS5pl7PRwpL6/kWSuEDf4NPXP91JUV2/qmoHsJ1T7wq6catmFeMM0HRHgIirrO3MUm6eZKVT3XWrYczFAUfureyiCzooIV9WOxwQGY7d10YgQ7K+hMZvNotLvhs2VJ4XoRJPapvFEK82xTfrtSvI262x59wtJpYpQo9pnSTxbLtkpdlVzr3UPXgdG0B42yhDqoCobuvOMEkTvQjGcI4p6VVa42nYs4SQZdub57se6z83Pu8kHBbQLKcRFNK2tDaXUtIMG7HtJ44mNcDVUnIbXV8u/kQvTPo2tyNjaYeENUw5Xx1D5Wfii2CS825s2kRQcuehf1EHV3ZdqRAjqMNWW2XCzCavdUlrfjqEuOGJSuZbqnp2hlyVZnuqbyLWlmatk0yazGg9Tz/JmdLNM595m3ih6CElZiT1u+ftEV/TV+nADp3zG0x5chI2TDgZQB9UpMD4fEeENvXf9yqp89FsDvimfQnGb11/VSGCZa40Bu4daIkyS/BOtgDhLsBaC+RDZfDPUGKpY1GKonIjrCZzrSqghMDfW6rSh6RctEbe+f0IK8iZSrzhgB1P0cK5c9C9qX3UPAHP8D79DrWpgFg/0jTCOuuCRuC+TcEMd0B/b18HMs1y9AuXsD/JZD0e1qC2WGF28VG9YWdGrV4YTknmSr5SvzZvcQjV2SDmYEbWHjdJTHdSGtCZbta7XjOYbrCxZIKq42UkBE+IE0oZl6IXTt1zf6jP4F3mch0N8i11uS77fh/kuB6laV1Ruz6p+JwjkuOWY1FhbEiCzRG5Z7PkwfGOKyhn9ECcp1EuQdNpSekqpWwBr8ahfjKQuAu5wlDy1u3/dHC6rgmuf/bHoUczUoB7xggIFxVEtjbv6pkyqb7rwhQ9Koo86MObOluX1KquLA2x1mtw+OxIyjHcbHO4tB4DJwtcn5u1CgCLbibe6xQV0Z0uVVelty7U4je1jdJYPCdDcG8V70HO/Ty4AG0fobud9c8D+drS9HGE2KTMvsDi98aQw9nIDzQ0Ak4bvoOI9fuVyH8Z/GRZQs43KYj5pDhPVVF6Euueae9fVAOMGsAXc3gHAHgMjTFf2pLPsueYGAAAAgD0DNDcAAAAATAnQ3AAAAAAwJUBzAwAAAMCUAM0NAAAAAFMCNDcAAAAATAnQ3AAAAAAwJUBzAwAAAMCUAM0NAAAAAFPif2N7sRFch84pAAAAAElFTkSuQmCC" alt="" name="图片 287" width="437" height="76" align="bottom" border="0" />

  

(8) Tracking.


Result:

code





[OpenCV] Identify and Track Specific Object的更多相关文章

  1. [Object Tracking] Identify and Track Specific Object

    Abstract—Augmented Reality (AR) has become increasingly popular in recent years and it has a widespr ...

  2. Learning to Track Any Object

    Learning to Track Any Object 2019-10-28 12:14:49 Paper: https://arxiv.org/abs/1910.11844 1.

  3. [Python] python vs cplusplus

    一些学习过程中的总结的两种语言的小对比,帮助理解OO programming. Continue... 字典 序列 --> 字典 Python: def get_counts(sequence) ...

  4. 本人AI知识体系导航 - AI menu

    Relevant Readable Links Name Interesting topic Comment Edwin Chen 非参贝叶斯   徐亦达老板 Dirichlet Process 学习 ...

  5. YOLO object detection with OpenCV

    Click here to download the source code to this post. In this tutorial, you’ll learn how to use the Y ...

  6. Object detection with deep learning and OpenCV

    目录 Single Shot Detectors for Object Detection Deep learning-based object detection with OpenCV   这篇文 ...

  7. Chapter 3 Discovering Classes and Object

    Chatper 3 Discovering Classes and Object Exercises: 1.What is a class? A class is a template for man ...

  8. [Object Tracking] MeanShift

    使用Opencv中均值漂移meanShift跟踪移动目标 Opencv均值漂移pyrMeanShiftFiltering彩色图像分割流程剖析 Opencv目标跟踪—CamShift算法 MeanShi ...

  9. How to set the initial value of a select element using AngularJS ng-options & track by

    原文: https://www.gurustop.net/blog/2014/01/28/common-problems-and-solutions-when-using-select-element ...

随机推荐

  1. 轻松了解Spring中的控制反转和依赖注入(二)

    紧接上一篇文章<轻松了解Spring中的控制反转和依赖注入>讲解了SpringIOC和DI的基本概念,这篇文章我们模拟一下SpringIOC的工作机制,使我们更加深刻的理解其中的工作. 类 ...

  2. 用ColorMatrix將Bitmap轉成灰度图

    在Android中,若想將整張圖片轉成灰階效果其實有更簡便的方式,只要透過ColorMatrix類別的setSaturation函式將飽和度設為0即可.(您也可以試試從0~1之間的值,看看不同飽和度的 ...

  3. jmap命令详解(转)

    1.命令基本概述 Jmap是一个可以输出所有内存中对象的工具,甚至可以将VM 中的heap,以二进制输出成文本.打印出某个java进程(使用pid)内存内的,所有‘对象’的情况(如:产生那些对象,及其 ...

  4. Android 使WebView支持HTML5 Video(全屏)播放的方法

    http://blog.csdn.net/zrzlj/article/details/8050633  1)需要在AndroidManifest.xml文件中声明需要使用HardwareAcceler ...

  5. Beego源码分析(转)

    摘要 beego 是 @astaxie 开发的重量级Go语言Web框架.它有标准的MVC模式,完善的功能模块,和优异的调试和开发模式等特点.并且beego在国内企业用户较多,社区发达和Q群,文档齐全, ...

  6. Solr5之Schema.xml详解

    schema.xml 是用来定义索引数据中的域的,包括域名称,域类型,域是否索引,是否分词,是否存储,是否标准化即 Norms ,是否存储项向量等等. schema.xml 配置文件的根元素就是 sc ...

  7. C++程序中调用MPI并行的批处理命令

    问题来源:在使用MPI时,将程序并行实现了,运行时需要在dos窗口下输入批处理命令,以完成程序的执行. 如:mpiexec -localroot -n 6 d:/mpi/pro.exe 但每次这样挺麻 ...

  8. 【最新图文教程】WinCE5.0中文模拟器SDK(VS2008)的配置

    http://www.blogbus.com/antiblood-logs/204402631.html 经过几天的查找,终于找到了一篇文章是讲VS2008 怎么集成wince5.0 的模拟器的,这里 ...

  9. 关于MYSQL中like 检索汉字问题。

    mysql中like’中国‘查询不出来结果 如果 like‘zg’就看查询出来结果. 查询了半天是由于mysql中编码的原因 解决办法: 进入mysql 输入命令:show variables lik ...

  10. js中“==”与"==="的区别

    首先,== equality 等同,=== identity 恒等. ==, 两边值类型不同的时候,要先进行类型转换,再比较. ===,不做类型转换,类型不同的一定不等. 一言以蔽之:==先转换类型再 ...